To no small extent, Americans have grown accustomed to being watched.
For more than a decade, CCTV cameras have recorded a hefty portion of many people’s public movements, while ubiquitous smartphones have made us all perpetually vulnerable to unsolicited documentation (if not, social media notoriety).
Until recently, however, technical limitations constrained the reach of government surveillance (at least, in the physical realm). Police may have been swimming in CCTV footage. But using such videos to track any given person’s movements was an extremely time-intensive endeavor. To do so, an officer would need to sift through hours of footage captured on many different cameras.
Yet AI is now making it possible for the government to trace ordinary citizens’ movements with unprecedented ease and precision. Or at least, this is what the security firm Flock Safety has effectively promised — and the company’s critics have loudly warned.
Flock provides police departments with networks of surveillance cameras — primarily, automatic license plate readers (ALPRs) that photograph each vehicle that passes them.
The firm’s main selling point is also its chief political liability: Its ALPRs log not only license plate numbers, but also generate textual descriptions of all vehicles they detect and store this information in a nationally integrated, searchable database. This makes it technically feasible for police to monitor the travels of most any driver with a few keystrokes.
Alas, some cops cannot be trusted with that power. In August, the Washington Post reported that at least 50 law enforcement officers had been charged or accused of using license-plate readers for illegitimate purposes, often to stalk their exes or romantic interests. Even more alarmingly, some police departments appear to have used ALPR data to surveil their own critics and protesters.
These revelations fortified an already growing movement against license plate readers. In August alone, more than 90 cities and counties canceled contracts with Flock. And this backlash has been remarkably bipartisan. Deep blue cities like Los Angeles, Austin, Texas, and Cambridge, Massachusetts, have backed out of partnerships with Flock, while Republicans in Florida have barred local police from installing ALPRs on state highways, and the Texas GOP has paused funding for Flock cameras.
The anti-ALPR movement is responding to real problems with how that technology has been deployed. And yet, according to Flock and many police departments, these cameras are also helping to nab car thieves and locate missing persons.
All this raises the questions: Do ALPRs really have significant public safety benefits? And if so, is there a way to have our license plate surveillance and civil liberties too?
To find out, I reviewed the latest academic research, dug through the worst horror stories in the news, and reached out to criminologists about the risks and rewards of ALPRs. Although the available evidence is limited, the technology appears to have modest — but genuine — crime-fighting benefits. And while the ALPR databases have been badly misused, this is in part because the tech has gone largely unregulated. With stringent safeguards, there may be a way to make it much harder for creeps and authoritarians to monitor law-abiding citizens’ comings and goings without forfeiting a useful law-enforcement tool.
On a late summer day in Chamblee, Georgia, Leslie Barrera was pushing her 1-year-old son Mateo in a stroller when a car pulled up next to her. A man sprung out of the vehicle, pointed a gun at Barrera, and tried to grab the baby from his carriage. But he’d chosen his victim poorly: Barrera charged him, wrested away his gun, and tried to shoot the kidnapper, only for the firearm to jam. A woman (oddly, disguised as a man) then emerged from the car and snatched the child. The baby-nabbers proceeded to pile back into their vehicle and speed away.
With the aid of surveillance cameras, police quickly identified the car as a maroon Acura SUV. Unfortunately, the abductors had swapped out its valid license plate with a paper dealer tag. Decades earlier, that might have delayed, if not thwarted, the recovery effort. But this was 2020 — and Chamblee police had access to a Flock ALPR system. By searching through its database of vehicle photos, the cops discovered a shot of the same Acura with its registered metal license plate from days earlier. The plate led them to the suspect’s name and address — and thus, within just five hours of his abduction — to Mateo.
Flock has a lot of stories like this. The company boasts that their cameras “supported more than 1 million criminal investigations” and helped locate “more than 10,000 missing persons” last year.
“Every single day, law enforcement across this country is using FLOCK technology to solve crime and find missing people faster,” Paris Lewbel, a spokesperson for Flock, told me.
The limited evidence suggests that Flock’s claims about its cameras’ public safety benefits are overhyped.
But Flock’s colorful anecdotes and raw tallies tell us only so much. A Flock camera can be used in an investigation without making a decisive difference in its outcome. Without ALPR photos, Chamblee police may still have been able to tie the maroon Acura to Mateo’s kidnappers.
To gauge Flock’s actual impact on public safety, we need (at a minimum) some quasi-experiments: When jurisdictions deploy advanced ALPR systems, do they see lower crime or higher clearance rates — both compared to their own past record and to simultaneous trends in Flock-less places?
There has been remarkably little research into these questions. But a recent study from the University of South Carolina’s Ian Adams and Scott Mourtgos sheds some light into them.
Drawing on Flock’s installation records, the criminologists identified the month that 216 law enforcement agencies activated their first camera. They found that during the first year after Flock deployment, these areas saw an 11 percent decline in motor vehicle theft, relative to similar places that remained un-Flocked. Jurisdictions that put up the ALPRs also saw the success rate of their car theft investigations rise by 16 percent.
These findings should be taken with a few grains of salt. For one thing, police departments will be more likely to invest in an ALPR system if they’ve got a serious stolen vehicle problem. And if car thefts in an area spike, they are liable to regress back toward historically typical levels, no matter what the local police department does.
What’s more, agencies will often install ALPRs as part of broader anti-vehicle theft efforts, which may include deploying more officers to high-crime areas, among other things. Adams and Mourtgos’s data suggests that such simultaneous actions may be responsible for a portion of their results: Although Flock adopters solved stolen car cases at a higher rate after putting up the cameras, this rise tended to begin before the ALPRs were installed.
Nevertheless, the working paper indicates that Flock cameras do make some difference. “We’re not talking huge numbers here,” Mourtgos told me, “but it’s not nothing either.”
And there is reason to think that ALPRs have greater potential to deter and solve crimes than existing results suggest, as police departments may be deploying them in suboptimal ways.
Consider a 2025 study of Atlantic City’s ALPR rollout. On paper, the municipality was an ideal candidate for the technology: As a barrier island, Atlantic City has only eight access points, so an ALPR network could easily capture every car entering and exiting the city.
As one would hope, the research found that car theft declined after the cameras were erected, although the authors could not rule out other explanations. Perhaps more significantly, however, they discovered that the cameras produced vastly more leads than the department was capable of logging or investigating. Between November 2022 and November 2024, the city’s ALPRs issued 12,384 stolen vehicle alerts, virtually all of which went unnoticed or ignored by department personnel; over the studied period, the ALPR system prompted only 72 vehicle stops, of which just 52 concerned stolen cars.
“In an ideal world, someone would be monitoring the alerts in real time and dispatching an officer, who would successfully make a traffic stop,” the paper’s co-author, Rowan University criminologist John Shjarback, told me. “But yeah, that kind of rarely happened.”
Shjarback concludes that the department lacked enough patrol officers to respond to a significant portion of alerts, while its civilian surveillance center monitors appeared to simply miss a large proportion of serious hits. “They have a lot to do in that real-time crime center,” Shjarback said. “There’s a relatively high amount of crime and gun violence and whatnot in Atlantic City. One or two retired officers on duty just weren’t enough to do the live monitoring.”
Similar operational flaws and resource constraints may have limited the efficacy of Flock systems in at least some of the areas analyzed by Adams and Mourtgos. Indeed, Mourtgos noted that many departments in his study lacked enough ALPRs to cover most significant thoroughfares. “Even in jurisdictions that are at the higher end on cameras, you’re still covering an extremely small minority of these roadway structures,” Mourtgos said. “So, that’s probably another reason why we see only modest effects.”
Taken together, the limited evidence suggests that Flock’s claims about its cameras’ public safety benefits are overhyped; its ALPR networks do not appear to be the “single greatest change” in policing tech “since DNA,” as the company touts on its website. But, as common sense might suggest, automatically logging all license plates on major highways and intersections seems to make it at least a bit harder to get away with stealing cars (and perhaps, babies).
Mass surveillance has its downsides
Of course, the fact that ALPRs offer some benefits to public safety does not mean that they’re necessarily worthwhile. Sewing a GPS chip into every American’s forearm would surely make crimes easier to solve and less tempting to commit. But most would regard such trackers as dystopian infringements on privacy and invitations to authoritarian control.
And Flock’s ALPRS are much the same, in the view of their staunchest critics.
The “DeFlock” movement’s fundamental argument is that the cameras give police departments more information than they can be trusted with. One danger is that wayward cops can exploit the data to stalk their exes. The more profound threat, however, is that police agencies will use ALPR systems to deter or punish lawful dissent.
And that hazard is not entirely hypothetical. After a writer named Canyen Ashworth published an op-ed criticizing local police in Lenexa, Kansas, that town’s police began tracking his movements with its ALPRs (apparently, because Ashworth’s column led the police chief to conclude, incorrectly, that he must have been the dastardly perp behind a recent spree of…unpermitted poster-hanging incidents).
More broadly, a 2025 investigation from the Electronic Frontier Foundation (EFF) found that more than 50 federal, state, and local agencies had run hundreds of searches related to protests or activist groups through Flock’s ALPR system. It’s not clear how many of these queries were motivated by an illiberal desire to monitor dissenters. In theory, a police officer could search for, say, “red sedan at No Kings protest” because a car of that description tried to run over protesters or committed some other criminal offense in the demonstration’s vicinity. And some of the searches tallied by EFF appear to fall into that category. But many others had no discernible purpose beyond the surveillance of activists.
We need to watch the watchmen
All this is unquestionably alarming. And if widespread misuse of ALPR networks were inevitable, then their costs to civil liberties would likely outweigh their modest (and as yet, not wholly certain) benefits for public safety.
But this probably isn’t the case. Rather, governments can likely limit ALPR’s downsides — while preserving their utility to law enforcement — by more stringently regulating the technology.
“In something like half of the states, there is no regulation. Virtually none, in our view, have adequate regulation.”
— Barry Friedman, founding director of NYU School of Law’s Policing Project
Until recently, legislatures had placed scant guardrails on ALPRs. As the Congressional Research Service noted in 2024, there is “no specific federal legislative framework” governing law enforcement’s use of such cameras. And most states have no comprehensive ALPR regulations. Thus, if we’re failing to prevent police departments from misusing these cameras, it may be because most state and local governments haven’t actually tried.
“In something like half of the states, there is no regulation,” Barry Friedman, the founding director of NYU School of Law’s Policing Project, told me. “Virtually none, in our view, have adequate regulation. The police decided to do this on their own. Them and their vendors made the decision and didn’t disclose what was happening.”
Fortunately, there is a long list of ways for policymakers to constrain abuse of ALPR data. To name just a few, governments could:
Virginia’s recently enacted ALPR law includes many of these provisions, while several other states have embraced a subset of these policies.
Some may still want to get de-Flocked
To be sure, for some, even heavily regulated ALPR systems will entail intolerable costs to privacy and unacceptable risks of authoritarian misuse. The American Civil Liberties Union (ACLU) supports efforts to regulate license plate readers, but only as a second-best alternative to banning the technology outright.
“No guardrails can completely address the chilling effect of mass surveillance,” Chad Marlow, senior policy counsel at the ACLU, said. “When people know that they are being surveilled all the time, they may not intellectually dig into the, ‘Well, what exactly is happening with this data? What’s it being collected for? How long is it being stored?’ The average person isn’t going to go through all those steps.”
Rather, Marlow argues, many will simply see cameras and fear that they’re being watched — and fearful of those doing the watching.
“Someone who is an alcoholic and wants to go to an AA meeting — but doesn’t want the public or any of their insurance companies or the government knowing they’re an alcoholic — and knows there’s a camera outside of the church that hosts the meeting may just say, ‘You know what? It’s really important for me to keep this struggle private. And so I can’t go to that AA meeting,’” he said.
These are legitimate concerns, although there is little hard evidence that license-plate readers have a chilling effect on protests or personal behavior. And given how much sensitive information people publicly share on social media — or willingly generate, through their internet activity — there’s some reason to doubt that many will refrain from lawful activity, merely because they spotted an ALPR by the side of the road. In fact, license plate readers have actually been in wide use for more than a decade and, until recently, few seemed to register their existence, much less, reorganize their lives around avoiding the cameras’ gaze.
Still, reasonable people can disagree about how to weigh ALPRs’ trade-offs. My point here is merely that governments may be able to secure modest but meaningful public safety benefits from the cameras — while greatly reducing their misuse — by giving regulation a chance. Using the ALPRs of 2026 probably doesn’t require accepting the authoritarian nightmares of 1984.
