Challenges and Risks

Along with these potential benefits come some difficult challenges and risks the education community must navigate:

Student cheating. Students might use AI to solve homework problems or take quizzes. AI-generated essays threaten to undermine learning as well as the college-entrance process. Aside from the ethical issues involved in such cheating, students who use AI to do their work for them may not be learning the content and skills they need.

Bias in AI algorithms. AI systems learn from the data they are trained on. If this data contains biases, those biases can be learned and perpetuated by the AI system. For example, if the data include student-performance information that’s biased toward one ethnicity, gender, or socioeconomic segment, the AI system could learn to favor students from that group. Less cited but still important are potential biases around political ideology and possibly even pedagogical philosophy that may generate responses not aligned to a community’s values.

Privacy concerns. When students or educators interact with generative-AI tools, their conversations and personal information might be stored and analyzed, posing a risk to their privacy. With public AI systems, educators should refrain from inputting or exposing sensitive details about themselves, their colleagues, or their students, including but not limited to private communications, personally identifiable information, health records, academic performance, emotional well-being, and financial information.

Decreased social connection. There is a risk that more time spent using AI systems will come at the cost of less student interaction with both educators and classmates. Children may also begin turning to these conversational AI systems in place of their friends. As a result, AI could intensify and worsen the public health crisis of loneliness, isolation, and lack of connection identified by the U.S. Surgeon General.

Overreliance on technology. Both teachers and students face the risk of becoming overly reliant on AI-driven technology. For students, this could stifle learning, especially the development of critical thinking. This challenge extends to educators as well. While AI can expedite lesson-plan generation, speed does not equate to quality. Teachers may be tempted to accept the initial AI-generated content rather than devote time to reviewing and refining it for optimal educational value.

Equity issues. Not all students have equal access to computer devices and the Internet. That imbalance could accelerate a widening of the achievement gap between students from different socioeconomic backgrounds.

Many of these risks are not new or unique to AI. Schools banned calculators and cellphones when these devices were first introduced, largely over concerns related to cheating. Privacy concerns around educational technology have led lawmakers to introduce hundreds of bills in state legislatures, and there are growing tensions between new technologies and existing federal privacy laws. The concerns over bias are understandable, but similar scrutiny is also warranted for existing content and materials that rarely, if ever, undergo review for racial or political bias.

In light of these challenges, the Department of Education has stressed the importance of keeping “humans in the loop” when using AI, particularly when the output might be used to inform a decision. As the department encouraged in its 2023 report, teachers, learners, and others need to retain their agency. AI cannot “replace a teacher, a guardian, or an education leader as the custodian of their students’ learning,” the report stressed.

Policy Challenges with AI

Policymakers are grappling with several questions related to AI as they seek to strike a balance between supporting innovation and protecting the public interest (see sidebar). The speed of innovation in AI is outpacing many policymakers’ understanding, let alone their ability to develop a consensus on the best ways to minimize the potential harms from AI while maximizing the benefits. The Department of Education’s 2023 report describes the risks and opportunities posed by AI, but its recommendations amount to guidance at best. The White House released a Blueprint for an AI Bill of Rights, but it, too, is more an aspirational statement than a governing document. Congress is drafting legislation related to AI, which will help generate needed debate, but the path to the president’s desk for signature is murky at best.

It is up to policymakers to establish clearer rules of the road and create a framework that provides consumer protections, builds public trust in AI systems, and establishes the regulatory certainty companies need for their product road maps. Considering the potential for AI to affect our economy, national security, and broader society, there is no time to waste.

Why AI Is Different

It is wise to be skeptical of new technologies that claim to revolutionize learning. In the past, prognosticators have promised that television, the computer, and the Internet, in turn, would transform education. Unfortunately, the heralded revolutions fell short of expectations. 

There are some early signs, though, that this technological wave might be different in the benefits it brings to students, teachers, and parents. Previous technologies democratized access to content and resources, but AI is democratizing a kind of machine intelligence that can be used to perform a myriad of tasks. Moreover, these capabilities are open and affordable—nearly anyone with an Internet connection and a phone now has access to an intelligent assistant. 

Generative AI models keep getting more powerful and are improving rapidly. The capabilities of these systems months or years from now will far exceed their current capacity. Their capabilities are also expanding through integration with other expert systems. Take math, for example. GPT-3.5 had some difficulties with certain basic mathematical concepts, but GPT-4 made significant improvement. Now, the incorporation of the Wolfram plug-in has nearly erased the remaining limitations. 

It’s reasonable to anticipate that these systems will become more potent, more accessible, and more affordable in the years ahead. The question, then, is how to use these emerging capabilities responsibly to improve teaching and learning. 

The paradox of AI may lie in its potential to enhance the human, interpersonal element in education. Aaron Levie, CEO of Box, a Cloud-based content-management company, believes that AI will ultimately help us attend more quickly to those important tasks “that only a human can do.” Frederick Hess, director of education policy studies at the American Enterprise Institute, similarly asserts that “successful schools are inevitably the product of the relationships between adults and students. When technology ignores that, it’s bound to disappoint. But when it’s designed to offer more coaching, free up time for meaningful teacher-student interaction, or offer students more personalized feedback, technology can make a significant, positive difference.” 

Technology does not revolutionize education; humans do. It is humans who create the systems and institutions that educate children, and it is the leaders of those systems who decide which tools to use and how to use them. Until those institutions modernize to accommodate the new possibilities of these technologies, we should expect incremental improvements at best. As Joel Rose, CEO of New Classrooms Innovation Partners, noted, “The most urgent need is for new and existing organizations to redesign the student experience in ways that take full advantage of AI’s capabilities.”

While past technologies have not lived up to hyped expectations, AI is not merely a continuation of the past; it is a leap into a new era of machine intelligence that we are only beginning to grasp. While the immediate implementation of these systems is imperfect, the swift pace of improvement holds promising prospects. The responsibility rests with human intervention—with educators, policymakers, and parents to incorporate this technology thoughtfully in a manner that optimally benefits teachers and learners. Our collective ambition should not focus solely or primarily on averting potential risks but rather on articulating a vision of the role AI should play in teaching and learning—a game plan that leverages the best of these technologies while preserving the best of human relationships.

John Bailey is a strategic adviser to entrepreneurs, policymakers, investors, and philanthropists and is a nonresident senior fellow at the American Enterprise Institute.

This article appeared in the Summer 2023 issue of Education Next. Suggested citation format:

Horn, M.B. (2023). Beyond the Big Yellow Bus: Can transportation apps reinvent how students get to school? Education Next, 23(3), 76-79.

Michael Horn is an executive editor of Education Next, co-founder of and a distinguished fellow at the Clayton Christensen Institute for Disruptive Innovation, and author of From Reopen to Reinvent. Daniel Curtis is a Master in Public Policy candidate at the Harvard Kennedy School of Government.

One of the hottest developments in education technology is schools banning technology.

After successive years of remote or hybrid learning, you might imagine tech-weary educators would be going after laptops and Zoom. But they are focused on cellphones, driven by three major concerns: students’ mental health, ability to stay engaged and learn during class, and struggles to focus for long stretches of time without task switching.

There’s an irony here. These bans are proliferating even as there are more useful, engaging, and instructionally sound mobile-learning applications than ever before. That suggests that cellphone bans, while useful in many school settings, shouldn’t be universal. We risk barring teachers, schools, and districts from productively using these apps to drive learning gains.

Where the Phones Aren’t

Some bans are blanket ones at the country or state level. In 2018, France passed a law that prohibited students under 15 from using phones, tablets, and smart watches in schools. The Australian state of Victoria bans phones in primary and secondary schools.

Some schools in the United States have taken similarly dramatic actions. Public schools and districts in Missouri, Pennsylvania, Maine, and New York State have instituted bans, often citing the devices’ ability to distract students from learning. And the Buxton School, a boarding school in Western Massachusetts, instituted a total ban on smartphones on campus after one of its students live streamed two others engaged in a fight. Students now are allowed “dumb” phones, but the constant alerts and capabilities of the smartphones are gone.

Other educators have counseled more moderate approaches to the same effect. Doug Lemov, author of Teach Like a Champion, wrote recently in Education Next that restricting cellphone use doesn’t “mean banning phones, it just means setting rules. These can take different forms, like setting up cellphone lockers at the main entrance, requiring students to use cellphone-collection baskets at the classroom door, or limiting use to cellphone-approved zones in the school building” (see “Take Away Their Cellphones” feature, Summer 2022).

One common method requires that students check their phones when they enter the school building. At several middle and high schools in and around Springfield, Massachusetts, phones are stored in a magnetic pouch that only educators can open until the end of the day. These metal pouches—like the one developed by Yondr, a San Francisco-based company founded in 2014—are commonly used at concerts and comedy shows to eliminate the distraction of mobile phones and allow people to engage fully in the experience before them. That same sales pitch has made pouches popular at many schools.

Although publications like the Boston Globe have editorialized in favor of these bans, not every school system is on board. Tragedies like mass school shootings in Uvalde, Texas, and Parkland, Florida, have given many parents pause about banning phones. The New York City Department of Education, for example, ended a ban on cellphones in schools in 2015, citing parents’ wishes to reach their children during the school day.

According to the federal education department, more than three quarters of public schools prohibited the non-academic use of cellphones during school hours in 2019–20. The phrasing suggests that in that number are schools that are outright banning phones, as well as those who have restricted phones but are consciously leveraging them for academic reasons.

Worries about Mental Health and Focus

Momentum to moderate cellphone usage stems from concerns about students’ mental health. American teenagers are experiencing a significant mental health crisis. According to the Centers for Disease Control, in 2021 44 percent of U.S. high-school students reported “persistent feelings of sadness or hopelessness” in the past year—up from 26 percent in 2009. Visits to emergency rooms for mental health emergencies and attempted suicides are up as well.

What is causing the crisis is disputed. Many pediatric groups and researchers—most prominently psychologist Jean Twenge, the author of the book iGen—have cited correlations in the rise of social media and smartphone use with teenagers’ increasing depression and anxiety to suggest that excessive smartphone and social media use is damaging a generation. But the reality appears more nuanced. One set of studies published in Child Development, for example, used a randomized design to tease apart the emotional impact of receiving fewer likes on social media. It found that although all students suffered a relatively immediate disappointment, it was only teenagers who were more vulnerable to social rejection that suffered a more enduring and significant negative impact.

Still, as Atlantic writer Derek Thompson observed, Twenge’s point may be misunderstood. “Social media isn’t like rat poison, which is toxic to almost everyone,” he wrote. “It’s more like alcohol: a mildly addictive substance that can enhance social situations but can also lead to dependency and depression among a minority of users.”

The other challenge with social media that Twenge cites isn’t the social media itself, but that it replaces sleep and in-person social interactions to such a high degree. Although some have argued there are silver linings to this—such as declines in binge drinking and sexual activity among teens—the impact on adolescents’ loneliness may be contributing to their decline in mental health. And if isolation is the true driver, of course pandemic-related lockdowns and school closures likely contributed to and accelerated some of these trends.

During class, student cellphones present two pressing challenges for teachers: disruption when students use their phones for non-academic purposes during class, and teenagers’ struggles to maintain the deep focus that rigorous academics demand. Sustained attention is unlike many students’ more typical mode of frequent task switching, where they toggle between different apps, which frequent smartphone alerts encourage.

As Lemov wrote, “This is no small thing. … The more rigorous the task, the more it requires what experts call selective or directed attention. To learn well, you must be able to maintain self-discipline about where you direct your attention.”

A lack of practice in focusing could damage students’ abilities to learn and do difficult work, in other words. And some studies have suggested that cellphone bans lead to better learning. One study of high schools in the United Kingdom, for example, showed that schools that banned mobile phones had improved test scores on a year-end test.

It’s All About the Learning Model

Yet while these concerns have led to more cellphone bans, there also has been an explosion in useful learning applications for mobile devices. Think of Duolingo for learning language, or ABC Mouse for learning elementary school subjects, or Quizlet for checking understanding. The ability to learn nearly anything from a phone is better than it’s ever been for all ages of learners.

With the active learning methodologies at the heart of these apps, the learning opportunities on mobile devices are in many ways superior to many of the more passive, video- and text-based ones built for laptops and personal computers. Cellphones may distract from traditional lectures or whole-class instruction. But they also command and can hold individual students’ attention—a precious resource that fuels learning, even if that learning doesn’t look like what we’ve seen before. Phones also may get in the way of students mastering required academic standards, while also connecting students to the information about which they are most curious.

How to explain the paradoxes?

In many learning models, there simply isn’t a productive place for smartphones. But is that the fault of the phone or the model?

Take a case-study classroom, for example. In it, all students are expected to participate in a group discussion to work through a specific situation with a joint set of case facts. If students are instead paying attention to their own devices, the conversation suffers and student learning slows as well.

Contrast that with a foreign-language class where all students work on personalized language modules on Duolingo, for example. They then put their phones away to participate in small-group conversations. (Even before smartphones, a version of this called “language lab” put individual students at headphone stations to work independently with the education technology of the day before rejoining group conversations.) The phone is central to the design of the learning experience. Of course, there’s a risk that students will work on tasks outside of the one assigned. But schools and teachers can use technology to block access to other apps or build on the social dynamics of the classroom to incentivize students to stay on task.

This phenomenon has been true with Internet-connected laptops as well. A 2016 study about a set of West Point classrooms showed that allowing computers when there wasn’t a key purpose for them diminished learning (see “Should Professors Ban Laptops?” research, Fall 2016). On the other hand, a blended-learning model like New Classrooms’ Teach to One relies on laptops to personalize math instruction for middle school students. Research has found students make outsized gains on math tests after successive years of participating in Teach to One classrooms.

One last argument for maintaining cellphones is that schools must teach students to use them responsibly. But many educators’ retort is that they are simply helping show students that there is a time and place for such devices—and school isn’t it.

In that respect, cellphone bans are following the larger trend of banning many things in schools—from books to speakers to certain kinds of speech or topics of debate. Cellphones may make for another easy bogeyman, but blanket bans are ill-informed and regressive. Though we might not see a big reversal in phone bans anytime soon, we should. Educators on the ground should choose for themselves when and whether to allow their students to carry cellphones to class, so they can leverage learning apps to help students make progress.

Michael Horn is an executive editor of Education Next, co-founder of and a distinguished fellow at the Clayton Christensen Institute for Disruptive Innovation, and author of From Reopen to Reinvent.

On the night of September 2, 2019, Assistant Superintendent for Compliance and Information Systems Bhargav Vyas received a system-failure warning for Monroe-Woodbury Central School District in Central Valley, New York. With his team, he chose to shut down the district’s entire computer network. Then, at 7:30 the next morning, he got a call from one of his leading techs, who was bringing the domain controllers back up after the previous night’s shutdown.

“Our biggest nightmare is here,” the tech said.

That was when Vyas knew a cybersecurity attack was happening.

* * *

Of the 17 industries studied by information-security company SecurityScorecard, the education sector ranked as the least secure in 2018, with the highest vulnerabilities present in application security, endpoint security, and keeping software up to date. Online learning, which has increased gradually over the past decade and significantly since March 2020, has only exacerbated the possibility of exposing staff and student data to unauthorized parties. The 2020 calendar year saw a record-breaking number of publicly disclosed school cybersecurity incidents—a grand total of 408 across 377 school districts in 40 states, according to the K–12 Cybersecurity Center. This represents an 18 percent increase over the 2019 calendar year total and a rate of more than two incidents per school day throughout 2020. These cyberattacks impacted taxpayers, district staff, and students, leading to school closures, millions of dollars stolen, and data breaches linked to identity theft and credit-card fraud.

Though these attacks affected only a small fraction of the overall number of schools and districts in the U.S., the frequency may increase as more lucrative targets, like corporations and banks, mount a better defense. According to the Consortium for School Networking’s 2019 K–12 IT Leadership Survey Report, rather “than focusing on corporate targets, which are devoting increased resources to cyber defenses,” hackers are turning to “more vulnerable sectors such as school districts, universities, and nonprofits.”

School districts’ networks are the perfect target for cybercriminals because they house a large amount of personal data but exist in a milieu not necessarily attuned to the threat of attack. While hackers’ individual motivations run the gamut, most of the attacks on school districts have been tied to cybercriminals looking for low-risk, high-return financial payoffs—which embattled district decisionmakers are willing to provide if it means keeping student and staff information private.

How Cyberattacks Happen: Phishing and Distributed Denial-of-Service Attacks

According to the Consortium for School Networking, more than 90 percent of cyberattacks in schools start with phishing campaigns, which include “spear phishing” and business-email compromise attacks. Spear phishing is characterized by a focus on specific individuals or groups within a larger organization; these attacks usually get a user to reveal personal information or install malicious software, or malware, on their computer. In a business-email compromise attack, cybercriminals impersonate a trusted party, usually a senior executive, to obtain payments or financial information. In a school-district context, business-email compromise is sometimes known as “Superintendent Fraud.”

Phishing attacks have become more sophisticated and difficult to detect. During the 2019–2020 school year, the San Felipe Del Rio Consolidated Independent School District was hit by a business-email compromise attack. A news release from the U.S. Attorney’s Office in the Western District of Texas explained how the attack worked: The school district’s comptroller received phishing emails from cybercriminals posing as officials at the financial institution to which the district makes bond payments. Three of those bond payments were then diverted to the swindlers’ financial account, which cost the district more than $2 million, according to the release.

Schools and districts can also fall victim to distributed denial-of-service attacks, as the Boston Globe reported Boston-area districts Mansfield, Medfield, and Norton did during the 2020–2021 school year. In this type of attack, a targeted flood of internet traffic disrupts network availability by overwhelming the system and surrounding infrastructure. As a result, users are prevented from accessing payroll platforms, student schedules, and email applications, all of which are necessary to conduct the day-to-day operations of the school.

This disruption can be just as beneficial for cybercriminals as it is for students, who may want classes cancelled or a break from remote learning. In September 2020, a series of DDoS attacks targeting the Miami-Dade County Public Schools were traced to the IP address of a 16-year-old student at South Miami Senior High School, according to a news release from the school district.

In addition to the complete paralysis of a school system, most criminal DDoS attacks have a second purpose: to breach data and expose confidential or protected information that can be viewed, shared, and used as ransom.

Ransomware

While school networks are offline during a DDoS attack, hackers use malicious software to encrypt districts’ data. Districts are then forced to pay hackers a ransom to regain access to their data—hence the term “ransomware.” As of August 2021, ransomware attacks have disrupted 58 education organizations and school districts in the U.S., including 830 individual schools, according to Politico. These attacks sometimes have devastating consequences: In March 2021, the Miami Herald reported that Broward County Public Schools could not pay a $40 million ransom, and 26,000 stolen files, which included student and staff Social Security numbers, addresses, and birthdates, were published online.

Most school districts lack strong security protocols because they have small IT teams and significant budgetary constraints, so it may seem from the outside that education organizations are not making cybersecurity a priority. This assessment, however, does not reflect the progress being made in districts across the country.

Thwarted Ransomware Attacks: Case Studies

Monroe-Woodbury Central School District

Back to Monroe-Woodbury Central School District. As soon as the IT team knew an attack was underway, they notified Superintendent Elise Rodriguez and the other assistant superintendents. Rodriguez informed the board of education, and then the public relations director and communications team contacted the business office, the district attorney, and the insurance company. Within an hour, the district had an incident response team working with Vyas to contain the attack, assess the damage, and develop a mitigation plan. The cybercriminals had just started targeting the district’s servers when the storage area network shut down, so, luckily, they had nowhere to go to do more damage.

Once the team determined that they had stopped the ransomware, the district focused on restoring weeks’ and months’ worth of data from offline and cloud-based backup systems. It took the district a couple of days to build up a Microsoft infrastructure, but by the end of the first week, 70 percent of mobile devices were up and running. At the end of the second week, all systems were up and running, and Wi-Fi was brought back online for 3,000 student and staff devices and computers.

Vyas reflected that it “was strategic on our part—not from the ransomware perspective, but a resources perspective—that we had an updated disaster recovery plan that identified the location of our data in all systems, as well as a robust redundancy system. This strategic move mitigated any further damage and communication.”

Prior to the attack, the district had also gotten an assessment of their network from the National Institute of Science and Technology. In January and March 2019, the IT team used the audit recommendations to “plug the holes,” which, in hindsight, could have been a factor in mitigating the effects of the cyberattack.

The IT team tried to learn from the attack. Though they had no proof, they believed that allowing personal devices to connect to the school network may have been a factor in the attack. The district therefore changed its policies: Only school devices were allowed to access the network, and guest networks were eliminated.

Rodriguez established scenario-based cybersecurity training, because “security is not just a technology concern; it’s a district concern.” Vyas continues to educate the school community, including the school board, about the latest trends in cybersecurity because, as he puts it, “people forget.”

Haverhill Public Schools

The attack on Haverhill Public Schools in Haverhill, Massachusetts, started shortly after midnight on Wednesday, April 7, 2021. By 2:30 in the morning, Director of Technology Doug Russell and Systems/ Network Engineer Don Preston had been alerted of system failures. They realized that this was more than just a standard system alert, and the team immediately shut down the network that connected all 15 district schools.

As soon as Russell and his team understood the extent of the attack, they notified Superintendent Margaret Marotta. Marotta then informed the Haverhill Public Schools School Committee and other critical stakeholders. She became the central communications person, thus enabling the IT team to focus on mitigating the problem. Within a few hours, the district had implemented its crisis-recovery plan and connected with its IT consulting company, which joined with local police, state police, the FBI, the Department of Homeland Security, and the Multi-State Information Sharing and Analysis Center, an organization that helps local, state, and tribal governments with cybersecurity-incident response and remediation, to assess the situation. After a few hours of evaluating the network, the Haverhill team determined that 140 of the 13,000 district endpoint devices had been infected with the ransomware. Much of the virus had been funneled into the districts’ virtual server environment, and most of those virtual servers had then detected the infection and shut down—exactly as they had been designed to do.

Authentication and rostering servers were up and running by six o’clock in the evening on the day of the attack. Five days after the incident, the internet had been restored in all 15 buildings, with 98 percent of the systems fully functioning. The email system took two and half weeks longer to be fully restored.

“One of the things that saved us was the transition to laptops for staff during the pandemic,” Russell said. Most staff members’ computers were not on the district network when the attack happened.

Russell added that another helpful mitigating factor was “a change that we made a couple of years ago” to “our whole virtual environment,” which meant there was no clear path for the ransomware to follow. Also, the cyberattack did not impact district financial records because the payroll system was hosted by the City of Haverhill on a completely different network. Finally, Russell explained that moving many systems to cloud hosting made the attack less severe than it would have been if the district had hosted all of those systems internally.

The Multi-State Information Sharing and Analysis Center’s investigation of the attack is ongoing, and the district has yet to confirm if any personal data was compromised. The team at Haverhill Public Schools did learn that they needed to upgrade existing systems and backup options, though. Before the attack, they had data snapshots, and the district operated with two different systems running at the same time. “So even though everything was still being snapshot and backed up, we realized that some of those systems, if they were to shut down, or if they would have been infected the wrong way, wouldn’t have gotten the last couple snapshots that we needed to recover,” Russell said.

Working with an IT consultant and the district crisis response team, as well as Marotta’s support and additional funding from the Haverhill School Committee, Russell and his team determined the need to increase redundancy and upgrade their anti-malware software and anti-ransomware software.

“I feel like if that would have been running, or something would have been running better, it probably would have stopped it even sooner, and we would have had fewer servers to restore,” reflected Russell.

What Can Districts Do?

Cybersecurity training

According to the October 2020 IBM Education Ransomware Study, which involved interviews with 1,000 educators and 200 administrators, administrators were “20 percent more likely to receive cybersecurity training than educators” though they were “still unaware of critical information relevant to protecting their schools.” Eighty-three percent of administrators expressed confidence in their school’s ability to handle a cyberattack, for example, but more than 60 percent of them did not know if their school had a mitigation plan.

About 90 percent of the time, cyberattacks happen due to human error, said Haverhill’s Russell. The source of the Haverhill Public Schools attack was a phishing email, which allowed the hackers to access a virtual remote server. In the wake of the attack, the school community took action and recognized the need for more cybersecurity training and, specifically, for secure password protocols through standardized requirements, such as making sure passwords are a certain length or have special characters.

Back up, back up, back up

A robust backup system is the best protection against an attack, and the most effective backup systems are a) cloud-hosted or offline, b) not tied to a district’s domain, and c) inaccessible from the district network. The Monroe-Woodbury and Haverhill districts have used secure backup systems with redundancy for years, so when their virtual servers were attacked, they were assured the recovery of their data. Russell added that “a backup is vital” and that “if districts are not backing up correctly, they will never be able to recover” from an attack.

Cybersecurity insurance

In 2020, the average cost of a data breach was $3.79 million for districts and other education organizations in the U.S., according to IBM’s annual report on data-breach costs. When the Manor Independent School District, a small district in Texas, was compromised by a phishing scam in January 2020, CBS Austin reported that it cost the community $2.3 million.

Most insurance companies now offer cyber liability insurance to school districts, for an average of $1,600 a year, according to AdvisorSmith. Though the cost varies based on size and location, districts could end up saving millions by adding this insurance to their yearly operational budgets. In November 2019, when Port Neches-Groves Independent School District in Texas was hit by a ransomware attack, a cybersecurity insurance rider on their district policy covered the $35,000 ransom demand, reported KBMT news. The district ended up getting back access to their systems—at the relatively low cost of a $2,500 insurance deductible. Cybersecurity insurance often covers not just the cost of the ransom itself, but of IT experts to analyze the breach, a marketing firm to manage the district’s response, and lawyers to advise the best next steps, as well lost revenue. The insurance also provides credit monitoring for the students and staff whose records were exposed by the breach.

Other best practices

Districts can reduce infections by filtering at the email gateway, maintaining updated antivirus and anti-malware software, and using a centrally managed antivirus solution. In addition, because some attacks are accidental, districts should apply the principle of data governance, or giving users access only to the data they need to do their jobs. It is also critical that districts maintain a robust asset-management system, retain and secure logs from network devices and local hosts, and baseline and analyze network activity to determine behavioral patterns. While districts may feel vulnerable and helpless in the wake of an attack, these proactive, rather than reactive, actions will determine the overall impact of a cybersecurity attack.

The Work of Many

Districts cannot fight off the hacker hordes alone. Though the ESSER fund provides billions of dollars to school districts for support in the wake of Covid-19, the money allocated to support broadband access, equipment purchases, and remote-learning infrastructure does not cover districts’ cybersecurity needs, such as upgraded firewalls. In June 2021, Senators Mark R. Warner and Susan Collins wrote a letter to Education Secretary Miguel Cardona advising the department to make Covid-19 relief funds available for cybersecurity resources. The letter also recommends that the U.S. Department of Education engage with school districts to increase awareness of the need for more robust cybersecurity measures.

On October 8, 2021, President Biden signed the K–12 Cybersecurity Act of 2021. This bill authorizes the Cybersecurity and Infrastructure Security Agency to study the specific risks impacting K–12 institutions, develop recommendations for cybersecurity guidelines, and create an online toolkit districts can use for implementation. Additionally, a bipartisan group of four House members introduced the Enhancing K–12 Cybersecurity Act in June 2021. This law would direct the Cybersecurity and Infrastructure Security Agency to create a cybersecurity information exchange, a K–12 incident reporting registry, and a $10 million, annual technology-improvement program.Organizations such as the Consortium for School Networking, State Educational Technology Directors Association, and National Association of State Chief Information Officers supported the bill.

When it comes to a cyberattack on a school district, it is no longer a matter of if but when. No longer does the danger zone start at the perimeters of district infrastructure and network. The danger zone now lies within the walls of school districts themselves. We must assume that, whether they are malicious or accidental, bad actors exist within our own systems.

Eileen Belastock is director of technology and information at Nauset Public Schools in Massachusetts.

This article appeared in the Spring 2022 issue of Education Next. Suggested citation format:

Belastok, E. (2022). “Our Biggest Nightmare Is Here” Cyberattacks are targeting school districts. How can schools respond to keep data and systems secure? Education Next, 22(2), 44-49.

The Covid-19 pandemic that prompted a nationwide shutdown of schools and a shift to online instruction in spring 2020 also prompted a wave of articles calling this instructional change a “natural experiment” that could be used to study the effects of online education. Yet the pandemic disrupted so many aspects of children’s academic, social, emotional, and economic lives that its broad scope poses serious challenges to isolating the causal impact of any specific change, such as the switch to remote instruction.

Educators and policymakers should proceed with caution when interpreting studies that attempt to identify such specific effects. Instead, researchers should focus on helping education leaders understand the overall impact of the pandemic on students, putting particular emphasis on discovering which groups have suffered the worst effects. The best evidence to date indicates that Covid-19 has had a substantial negative impact overall and has disproportionately harmed the learning of disadvantaged students. Continued research in this direction could provide a sharper picture of which students have faced the most severe challenges under Covid-19, pointing the way toward how best to allocate resources to address learning losses.

Econometric Challenges

In econometrics, an “instrument” is a variable that has a direct impact on the probability that an individual is treated by a policy of interest. For example, some people have suggested that the pandemic could serve as an econometric instrument to study the effects of online learning, since the pandemic dramatically increased the number of students learning virtually in 2020. Major concerns arise, though, in using the pandemic as an instrument to study the impacts of such a policy change. These concerns relate to the fact that a rigorous causal study must have both internal and external validity. Internal validity requires that econometric analyses capture the true causal impact of only the policy change of interest—in this case, the shift from in-person to online instruction—rather than the possible effects of other contemporaneous changes. External validity requires that the estimated effects of a policy change induced by the pandemic would accurately predict the effects of similar treatments in other contexts, such as a typical school year. The nature of the pandemic presents serious challenges to both the internal and the external validity of most research designs, including the use of the pandemic as an instrument.

Challenges to internal validity. To understand why many studies of pandemic-induced policy changes could suffer from serious threats to internal validity, first consider a common research design with notably strong internal validity: a randomized experiment. If researchers were to use a randomized experiment to estimate the impact of remote instruction on student learning, they would need to assign students at random to the treatment group (students who receive remote instruction) or the control group (students who receive in-person instruction). Assigning the treatment at random ensures there are no systematic differences between the two groups other than the treatment itself. A randomized experiment has high internal validity because it clearly isolates the impact of a particular treatment.

Quasi-experimental research designs, or “natural experiments,” take advantage of variations in treatment status that occur as a result of policy changes or other “natural” phenomena outside of a researcher’s control. While natural experiments eliminate the need to actively assign individuals to treatment and control groups, they typically face greater threats to internal validity than do randomized experiments. One common type of natural experiment uses an econometric instrument to estimate the effects of a particular policy change. The onset of the pandemic holds obvious appeal as an econometric instrument for studying the effects of online instruction, since the crisis caused a sudden shift to remote teaching. A key assumption of this research design, however, is that the policy change of interest (the shift to online learning) does not coincide with other relevant changes. In econometrics, this is known as the “exclusion restriction,” which requires that the econometric instrument (the pandemic) affect the outcome of interest (student learning) only through the policy change of interest (the shift to online learning) and not through other channels.

While the Covid crisis did spur the shift to online instruction, it fails the exclusion restriction because of the many contemporaneous changes that likely also affected student learning. Students shifted to remote learning as their parents lost jobs, as their family members suffered Covid’s health effects, and as they lost the ability to leave the house and see friends, among other significant changes to their lives. If Covid-19 did affect student learning, it would be difficult to attribute the changes in outcomes to remote instruction rather than any of these other contemporaneous factors. We illustrate this in Figure 1, which shows the potential use of Covid-19 as an econometric instrument for remote instruction. The exclusion restriction requires that there be no “causal arrow” between the other channels affected by Covid-19 and student learning, an assumption that is certainly violated based on both common sense and prior empirical evidence. It may be possible to estimate the overall effect of Covid-19 on student outcomes, but attributing that effect to any one channel is likely impossible.

We can illustrate the violation of the exclusion restriction with an example from our own recent research into Covid’s impacts on household Internet-search behavior. In that work, we show that Covid-induced school closings caused parents to seek out online learning resources that might compensate for lost in-school instructional time. An example of this can be seen in the top panel of Figure 2, which shows a large increase in Google searches for “online learning” that corresponded precisely with the timing of the pandemic outbreak in the United States. This provides evidence that the Covid-19 crisis indeed represents a sudden shock to the demand for online learning resources.

At the same time, however, there were many other changes in students’ lives that are reflected in Internet search behavior. Data show, for example, that there were sudden and contemporaneous increases in Google searches for terms relating to the economic condition of households, such as “unemployment insurance” and “food stamps.” The pandemic changed students’ educational experiences but also generated a considerable economic shock to many households. These large, simultaneous changes make it difficult to separate the effects of one shock from another.

Challenges to external validity. The unprecedented circumstances surrounding the Covid-19 crisis also present serious challenges to external validity. Researchers typically examine whether the context and implementation of a policy shift are representative of potential future enactments of the same policy. Neither the context nor the implementation is likely to be representative in this case.

First, the learning environment during the pandemic is unlikely to generalize to typical school years because of the many changes in students’ lives that likely put a strain on their capacity to learn. For instance, students and young adults have reported substantial increases in anxiety and depression during the pandemic. Second, pandemic-induced policy changes were implemented in a way that is unlikely to resemble a more carefully planned implementation of the same policy in a typical year. For example, the pandemic-induced shift to online learning required teachers, with no advance warning, to quickly redesign lessons originally intended for in-person instruction. Under normal circumstances, teachers would have been afforded time to prepare lessons specifically for online instruction. Even in the fall of 2020, there was still substantial uncertainty around schooling logistics and instructional modality, making it difficult for educators to plan instruction effectively in advance. The unprecedented circumstances of the pandemic and the corresponding ad hoc policy shifts are therefore unlikely to generalize to well-planned policy changes in a typical school year.

The Overall Impacts of Covid-19 on Students

Although it is nearly impossible to disentangle the effect of any specific policy, the overall effect of the pandemic—including economic, health, social, and educational changes—is something we can attempt to assess. Moreover, as the pandemic continues to disrupt daily life more than a year after schools first closed, it is increasingly important to understand the impact of the pandemic itself. In addition to the short-run impacts on learning, a range of prior evidence suggests that the effects of health, social, and economic experiences in early childhood can persist into adulthood.

Emerging evidence on the short-run impacts shows that Covid-19 has caused substantial disruptions to students’ learning, particularly for disadvantaged students. Raj Chetty and colleagues find that student progress on Zearn, a popular online math platform, decreased by roughly 30 percent over spring 2020, with children in the lowest-income schools seeing progress drop by 50 percent and those in the highest-income schools quickly recovering to pre-pandemic levels. Nationwide evidence from fall 2020 MAP Growth assessments suggests that students lost ground in mathematics and that reading losses were concentrated among Black and Hispanic students in upper elementary grades. Recent work in Georgia suggests that students lost further ground as the school year progressed through the winter of 2020, with such losses larger among low-income, Black, and Hispanic students. Our research reveals one potential reason for these disparities: when the pandemic first struck, demand for online learning resources increased substantially less in low-income areas than in high-income areas of the United States (see “What Google Search Data Reveal about Learning During the Pandemic,” web only).

Education researchers predict that the pandemic will substantially increase achievement gaps between students from low- and high-income households, even beyond the 2020–21 school year. The best evidence to date shows that Covid-19 not only reduced the learning of the average student compared to typical school years, but that it also increased achievement gaps by disproportionately harming disadvantaged students.

What Comes Next?

Instead of framing the pandemic as a “natural experiment” for studying specific educational interventions, we propose that researchers and policymakers focus on measuring the overall effects of the pandemic itself. We believe it is possible to generate econometrically sound estimates of the overall social, emotional, and academic costs of the pandemic. The pandemic is, however, too large and unprecedented a shock to give us precise insights into individual aspects of children’s educational experiences that have changed. Too many things changed all at once.

After more than a year of pandemic-induced restrictions and shutdowns, there is reason for guarded optimism. Vaccinations have become widely available in the United States, Covid cases, hospitalizations, and deaths here have dropped rapidly, and the era of widespread school closures and fully remote instruction is ending. The educational effects of the pandemic are, however, likely to linger unless we identify the students who have been most adversely affected and provide additional resources to reverse these impacts. The best evidence to date shows that Covid has not only impeded the learning of the average student, but also widened achievement gaps by disproportionately harming the learning of low-performing students. Educators now face the challenge of not only making up for lost instructional time but also closing gaps that are even wider than usual. Though choices of how best to remedy these losses may be best left to individual states, districts, or schools, substantial resources should be devoted to these efforts. Without such investment, particularly among students who have experienced the greatest setbacks, we will likely enter an era of increased educational inequality persisting beyond the return of fully reopened schools.

Andrew Bacher-Hicks is assistant professor at Boston University Wheelock College of Education and Human Development, where Joshua Goodman is associate professor of education.

Step into Nicole Reitz-Larsen’s classroom in Salt Lake City’s West High School and see students grooving to “Single Ladies” or zigzagging to execute one of LeBron James’s handshakes. You might think it’s a dance class. It’s not.

Reitz-Larsen is teaching computer science through movement. The former German-language and business instructor found that linking difficult concepts such as algorithms and the binary system to students’ interests helps the students grasp a topic that many were leery about before they stepped into her class.

“I’m always thinking about how to sell it to my students,” said Reitz-Larsen, who learned how to teach the complex subject in three months after administrators asked her to pioneer it at West. “You have those kids who say, ‘I’m never going to use this.’”

Young people who are glued to their phones and laptops for many of their waking hours are often apathetic when it comes to figuring out what makes their devices tick. About one of every three girls and half of boys think computer science is important for them to learn, according to a 2020 Google/Gallup, Inc., survey of 7,000 educators, parents, and students.

The finding came four years after President Barack Obama declared that computer science is as essential for K–12 students as reading, writing, and arithmetic. The announcement gave momentum to a computer-science-for-all movement and propelled industry-backed nonprofits such as code.org to the forefront of debates about what should be taught in schools. Joe Biden, both as vice president and during his 2020 presidential campaign, emphasized his support for having K–12 students learn the subject.

The effort is part of a broader attempt to overhaul and update the U.S. education system. Proponents argue that it’s time to amend the public-school curriculum to reflect life skills demanded by the ever-changing Information Age. Such a reframing is necessary, they say, to ensure students can compete for positions focused on cloud computing, artificial intelligence, and mobile-app development.

After Obama’s high-profile endorsement of code.org’s mission, the organization joined educators and other advocates to help persuade state legislatures to allocate millions of dollars toward new laws that advance its vision that “every student in every school has the opportunity to learn computer science.”

Some states made more progress than others. Thirty-seven adopted computer-science standards for K–12, and 20 required all high schools to offer the subject. In Nevada and South Carolina, the discipline is now a graduation requirement. New York City committed to making the subject available at every K–12 school by 2025. New rules such as these helped drive about 186,000 students to take Advanced Placement computer-science tests in 2020, nine times more than in 2010.

A 2020 report from code.org found that 47 percent of the nation’s high schools teach computer science. Despite a growing belief among parents, administrators, and students in computer science’s benefits, and millions of dollars allocated to offering it in K–12 schools, gaps in access and participation among Black, Hispanic, and white students persist.

Today, computer-science-for-all leaders acknowledge they’ve hit a plateau and that they need more-widespread buy-in from lawmakers and educators and increased funding to overcome disparities in the U.S. education system that fall along racial and socioeconomic lines.

“Early on, we got all these early-adopter states, school districts, and teachers raising their hands, and there was a frenzy of activity. Now we’re moving into people being told to do it,” said Ruthe Farmer, chief evangelist for CSforAll, a New York–based nonprofit. “The skepticism around how we’re going to get this done is still there.”

Constraining the movement’s growth are a scarcity of well-qualified teachers, particularly in math and science, and competition for resources in cash-strapped school districts. Hard-fought progress was also stalled by the coronavirus pandemic, when states such as Colorado and Missouri reallocated or froze funding dedicated to broadening access to the subject in K–12.

At the same time, Covid-19 laid bare long-standing inequities in access to laptops and high-speed broadband connections necessary to expand availability across cultures and to English language learners, rural students, and those with disabilities.

As advocates remain focused on quantifying computer science’s inroads into public schools, there is a dearth of research that evaluates the effectiveness of different instructional methods for developing such skills. Assessments with which to measure curriculum quality, reach, and relevance are also largely absent.

What’s more, there is no consensus on a robust definition of computer science, with some principals assuming courses that teach office skills will suffice. Some advocates now say it’s time to step back and reassess whether computer-science education really is “for all.”

“We are going really, really fast in trying to get computer science into schools and there absolutely is an urgency,” said Julie Flapan, director of the Computer Science Equity Project at the University of California, Los Angeles.

“We have to have conversations about what’s good for computer science and what’s good for kids. We wrestle with these tensions,” added Flapan, who is also co-director of the CSforCA Coalition. “We need to be mindful about not creating unintended consequences.”

The tradeoffs of adding the subject in K–12 schools are now becoming apparent. In California, computer-science enrollment growth came at the expense of social studies, English/language arts, foreign language, and arts courses, researchers found. The field’s supporters stress the subject must be taught alongside, or integrated into, other core courses, rather than replacing them.

“I don’t think math class or computer science should be an either-or situation,” wrote Jane Margolis, a senior researcher at the University of California, Los Angeles, and author of Stuck in the Shallow End: Education, Race, and Computing, via email. “Students need math, and they need computer science in today’s world.”

Or Do They?

Some scholars, though, reject the notion that all K–12 students should learn computer science, comparing the movement to other industry-driven efforts to add vocational training to public schools that led to agriculture, shop, and home-economics classes.

“Why would you teach coding to little kids, or even big kids, unless they want to be programmers?” said Larry Cuban, a professor emeritus of education at Stanford University.

“Because schools are politically vulnerable, this current push for coding for all, for computer science for all, is part of a historical trend to alter schools’ curriculum to meet the needs of a vested interest,” added Cuban, author of The Flight of a Butterfly or the Path of a Bullet? Using Technology to Transform Teaching and Learning.

The debate over the merits of computer science for all in K–12 schools is also occurring globally, said Andreas Schleicher, director for education and skills at the Organisation for Economic Co-operation and Development. He said teaching coding is not useful for K–12 students because coding languages change often.

“There is a debate about this that is similar to the one in the U.S.—you have here in Europe a technology industry that is very much pushing for these skills,” said Schleicher, “and educators are pushing back and saying they don’t want to teach for today’s workplaces; they want to teach for tomorrow’s workplaces.”

Schleicher said he does believe that students should learn how to think computationally, particularly as that kind of thinking applies to data science and artificial intelligence. But, he said, using computers just to teach with the tool of the day, like a pen in the 17th century, or a typewriter in the 1900s, is a “time-bound phenomenon” with little relevance for students’ futures.

These arguments point up a fundamental challenge for proponents of the computer-science-for-all movement: defining what the subject is and how it should be taught.

What Is Computer Science?

There is consensus on what computer science is not—basic computing skills such as Internet searching, keyboarding, and using a spreadsheet—but no universal agreement on what it actually is. There are many different definitions, largely because decisions about what and how students are taught are made at the state, district, and school level. New York emphasizes digital literacy; Texas incorporated the discipline into its technical career standards.

Many proponents of the computer-science-for-all movement, which began in the early 2000s, spend considerable time trying to dispel the notion that it’s solely about learning coding.

Coding languages used in developing software are a tool for computer science, educators say, just as arithmetic is a tool for math and words are a tool for verbal communication. At its core, computer science is about learning how to create new technologies, rather than simply using them, advocates stress. It strives, for example, to teach students how to design the software that will make the spreadsheet.

Just as important as coding, backers add, are foundational concepts such as computational thinking. This approach to computer science provides students with a way to solve problems by breaking them down into parts, and it can be integrated across subjects as early as kindergarten.

In some states, computer-science standards overlap with math standards and involve concepts such as sequencing, ordering, and sorting. Standards can also include science concepts such as devising a hypothesis, testing it, refining it, and perhaps redesigning an experiment after “debugging.”

Just as students should learn how to read, analyze, and write text effectively, they need exposure to computer science to become informed digital citizens who understand how technology impacts their everyday lives, said Yasmin Kafai, a professor at the University of Pennsylvania Graduate School of Education.

Kafai, co-author of Connected Code: Why Children Need to Learn Programming, said that a big part of the world nowadays is the digital public sphere, “where we interface through machines.”

“We want to provide students in K–12 with an understanding of what that actually is—it’s a designed world, and it makes a difference when you understand how it’s designed,” she added. “It helps to understand its limitations.”

Such skills might help young people feel comfortable working with large amounts of data and empower them to push back against the negative impacts of technology.

After defining what computer science means for their districts, administrators need to decide what outcomes they hope to achieve for their students, advocates say. They acknowledge that in the early years of computer-science education, they overemphasized its role in training future programmers. With a shortage of tech workers in many regions, workforce development has been a powerful argument for offering computer science.

Jobs in computer and information technology are among the best paying in the United States, with the median annual salary for these occupations clocking in at $91,250 in May 2020, more than twice the median annual pay for occupations overall. The U.S. Bureau of Labor Statistics projects that such jobs will be among the fastest growing in the next decade. Yet the vocational approach to computer science turns off some administrators, who believe that K–12 education is more than just training young people for jobs.

“We’ve been using the workforce argument a lot when we talk about expanding computer-science education,” said Leigh Ann DeLyser, co-founder and executive director of CSforAll. “Yet the national survey of school administrators from NCES shows that less than half of school administrators see workforce development in the top three priorities for student education. We were putting out a message that was completely mismatched from what administrators thought was the purpose for kids to be in school.”

CSforAll has worked with more than 146 public school districts serving about 2 million students to conduct mapping exercises that helped administrators shape their computer-science curricula to match their school’s vision for what their students should get out of the subject.

Just like states’ definitions of computer science, visions that undergird state standards vary widely. In Nevada, it’s about civic engagement. In Indiana, school reform. In North Dakota, cybersecurity.

These values and others expressed in state guidelines, such as equity, literacy, innovation, and personal fulfillment, are key to developing curricula that appeals to all students, according to a CSforAll study.

Curriculum Choices

Computer-science curriculum choices abound, with both commercial programs and free options available. While apparently no one tracks which curricula are used most often, the free introductory courses offered by code.org are very popular and currently used by about 1.3 million teachers.

Schools have also widely adopted curricula offered by Project Lead The Way, Codelicious, and Code Monkey. Some curricula feature easy-to-use block-coding programs, such as the MIT-developed Scratch and Google’s Blockly, that allow programmers to drag and drop blocks containing instructions to create animated stories and games.

Some curricula integrate computer science into other subjects. Bootstrap designs curricular modules for algebra, history and social studies, business, and physics classes that explicitly align computer science concepts with those disciplines. Project GUTS helps students create scientific models using web-based software.

Advocates suggest it’s best to cultivate students’ interest in computer science in elementary school, citing research that the earlier children are exposed to the subject the more likely they are to want to take it in middle and high school. Teaching computer science in younger grades is still not common, however.

To broaden access to the subject for high school students, researchers developed more basic curricula. Exploring Computer Science, which includes web design, data analysis, robotics, and programming through Scratch, is used by districts in Los Angeles, Spokane, Chicago, and New York City, among others.

Another course, AP Computer Science Principles, was designed, like Exploring Computer Science, in part to interest more women and minorities in the discipline. Teachers can use a variety of curricula to teach the AP course that includes lessons on how to design and program “socially useful” mobile apps, write and talk about ideas, and collaborate with peers. In 2016–17, the course’s first year, AP Computer Science Principles attracted more students than any other AP course debut in history.

Even as more schools and teachers use such wide-ranging curricula, determining their quality is difficult, noted Allison Scott, chief executive officer at the Kapor Foundation, an Oakland nonprofit that researches diversity in technology. “I think there is still a lot we don’t know about the effectiveness of computer-science curriculum overall, due to a few key challenges,” Scott wrote via email, “including the lack of consistent assessments for computer-science courses and the lack of information on the curriculum landscape.”

A December 2020 report from the College Board found that students who took computer-science principles were three times more likely to choose the major in college than peers who didn’t take the course—16.9 percent versus 5.2 percent. Even so, the nonprofit has no information on which curriculum was used in AP classes—it endorses a range of options for teachers to choose from—and whether any resulted in better outcomes, Scott wrote.

Researchers who study how computer-science curricula is used in elementary and middle schools found that teaching approaches range from very scripted lessons to open-ended ones where students are asked to create projects on a blank page.

“In our study, we found really big gaps in learning—for some kids you give them a blank screen and they are not going to push themselves,” said Diana Franklin, an associate professor in computer science at The University of Chicago. “The way people are teaching and the curriculum they use is not sufficient—there is room for improvement.”

Instead of randomly clicking on blocks in an open-ended approach to coding, she said, students first need to be given an example project that uses prompts to walk them through the steps of programming something on the screen and that requires them to write down their observations and predict what will happen with each step.

To track students’ progress and understanding of the material, the discipline needs written assessments that are validated, Franklin said. Such tests would allow schools to publish computer-science successes, she added. To help students score well on such assessments, schools would be incentivized to improve their curriculum, she added.

The Teaching Gap

Often, it’s difficult to implement a computer-science program district-wide, and it falls to teachers to promote the subject in individual schools. Many find the discipline intimidating because they weren’t trained in it in college. If teachers don’t fully understand the content, they won’t be able to teach it well, said Anne Ottenbreit-Leftwich, an associate professor of instructional systems technology at Indiana University Bloomington.

More than one in three public school teachers interviewed for the 2020 Google/Gallup study said the quality of computer-science instruction that students received in school was fair or poor. Researchers who study the subject said that, often, quality suffers because teachers are expected to add computer science to their already jam-packed schedules.

“We have unfair expectations for our teachers—we say they have to have every student this far on literacy and students this far on math,” Ottenbreit-Leftwich said. “There is not enough time in the day for professional development for computer science, then there is not enough time to teach it.”

Teachers who volunteer to teach the discipline or are assigned the responsibility often receive several weeks of training.

“We are very much behind the curve in growing the numbers of computer-science teachers,” said Melissa Rasberry, a consultant with the American Institutes for Research who serves as principal investigator for CSforAll Teachers. “Very few programs are university based—you could count them on one hand at this point.”

Seeking Equity

After teachers are trained, they often find that few students understand what their computer-science classes are about. Stereotypes abound around which groups are suited to excel in the discipline.

“I believe that youth today understand that it is mostly white and Asian males who fill the ranks of the tech industry,” wrote Margolis, the UCLA researcher, via email, “and that this negatively impacts their sense of identity and agency in this field.”

Equitable access to computer science in K–12 schools has proved among the thorniest challenges for the computer-science-for-all push, even as proponents say it’s at the heart of the movement.

Disparities in computer-science course participation are difficult to pin down, since most states don’t collect demographic data on student enrollment in such courses, code.org’s 2020 report found. The number of Black, Hispanic, and Native American students taking AP computer-science exams remains low across many states, with several states reporting zero Black or Hispanic female students sitting for such tests in 2020.

From California to New York, advocates recount how they celebrated hard-fought gains in getting courses introduced in high schools, only to see them populated largely by students from middle- and upper-income families. Chicago Public Schools moved the needle on equity, but only by requiring that all students obtain computer-science credits to graduate.

“We set forth with a goal of changing the face of computing to make sure generally more girls, and more Black and brown kids, were taking computer science, and we’ve seen that,” said Lucia Dettori, an associate dean at DePaul University and a founding member of the Chicago Alliance for Equity in Computer Science. “But I know from talking to people around the country that just adding the class doesn’t mean more people are taking it.”

Educators are working with nonprofits such as Black Girls Code, Girls Who Code, and Latina Girls Code to engage a wider range of students. Researchers found that many girls and students of color are looking to use technology for a larger social purpose.

Extracurricular activities such as Hour of Code, Computer Science Education Week, and robotics competitions helped to expose nearly 7 in 10 middle and high school students to the topic, Gallup found. Such programs can nurture interest in the discipline and perhaps prompt parents and students to demand that it be made part of the curriculum, advocates say.

At Salt Lake City’s West High, Nicole Reitz-Larsen is constantly searching for culturally relevant ways to draw more 7th through 12th graders into her computer-science classes. Like teachers nationwide, she recently turned to CodeScty, which uses hip hop to “develop core competencies in computational thinking and coding,” according to their website.

She also enticed students on their way to eat lunch outside, or in the cafeteria, or in commons area, to participate in “robot challenges.” In one instance, students programmed robots to play in hallway soccer games on “fields” created with painter’s tape on shower curtains.

“People walking in the hallways, or other classes, would want to see what my students were doing, and it would interest them in checking out the class,” Reitz-Larsen said, adding, “we never have enough desks for students.”

The educator also works with code.org to train fellow teachers nationwide and answers their questions about how to develop engaging curricula and convince their colleagues that computer science should be more than an elective.

“It’s been eight years since we started teaching it at West, and it’s taken that long to convince counselors in my school that anyone can do computer science,” said Reitz-Larsen. “Now, whoever is in the hallway, I have the same representation in my classroom—I purposefully make sure students are comfortable in my classes, and I tell them to bring their friends.”

Jennifer Oldham is a Denver-based independent journalist who specializes in coverage of government, inequality, and the environment.