LLMs and Contextual Integrity

I have been thinking a lot about AI and integrity. Part of that is contextual integrity. I recently found two papers on the topic. "CIMemories: A Compositional Benchmark for Contextual Integrity of Persistent Memory in LLMs": Abstract: Large Language Models LLMs increasingly use persistent memory...

Hacking Public Wi-Fi DNS to Steal Credentials

Criminals are hacking into public Wi-Fi devices--at hotels, conference centers, and so on--around the world and changing their DNS settings. The goal is to redirect users to fake login pages and steal their credentials...

Friday Squid Blogging: Searching for the Colossal Squid

Fascinating video about searching for life undersea. The video basically makes the point that our bright white searchlights are scaring everything away, and that red light is more neutral. That, plus bait to attract sea creatures, is teaching us a lot about what's going on down there. Lots of...

Upcoming Speaking Engagements

This is a current list of where and when I am scheduled to speak: I’m speaking, signing books, and participating in panel discussions at LAcon V in Anaheim, California, USA. My full schedule is here. I'm speaking online via Zoom at a League of Women Voters event on Tuesday, September 22, 2026, at...

If the Markets Reject OpenAI and Anthropic, the US Should Nationalize Them

This essay was written with Nathan E. Sanders, and originally appeared inThe Guardian. OpenAI, and then Anthropic, were each formed by AI developers who feared unrestrained corporate AI development--specifically, that companies like Google and Meta would steer the technology towards deleterious,...

Separating AI’s Technological Problems from Its Capitalism Problems

This essay was written with Nathan E. Sanders, and originally appeared inTech Policy Press. AI represents the first time we humans can do cognitive work outside of our bodies at scale. The only comparable moment is the early years of the industrial revolution, when new technologies like the steam...

Prompt Injections for Defense

This seems to work: Researchers from Tracebit on Monday said they found that placing prompt injections alongside passwords, cryptographic keys, and other secrets stored on Amazon Web Services was often all that was needed to shut down attacks from AI hacking agents. The prompts direct the attacki...

AI Genie in the Wild

When I give talks about AI genies, I use this sort of example as a hypothetical. It's happened. The story is from Australia. Someone named Andrew tasked OpenClaw to book gym classes for him. And…. Minutes later, his AI agent reported it had discovered a way to book Andrew into classes several wee...

AI for Military Support

Interesting empirical research: "Black Box Warfare: Human Judgment and Military Decision-Making in the Age of AI." Abstract: How is AI transforming decision-making in modern conflict? This study provides a unique empirical window into that question by deploying a high-fidelity replica of an AI...

Python Now Has a Post-Quantum Encryption Library

This is good: Post-quantum cryptography is now one pip-install away for the entire Python ecosystem. With funding from the Sovereign Tech Agency, we implemented support for ML-KEM, the NIST-standard key-establishment primitive, and ML-DSA, the NIST-standard digital-signature primitive, in...

Friday Squid Blogging: Arctic Bobtail Squid Video

Nice video of the Arctic bobtail squid. As usual, you can also use this squid post to talk about the security stories in the news that I haven't covered. Blog moderation policy...

ICE Is Buying Access to Credit Card Records

Through data brokers, ICE is buying the information you provided to open a credit card...

Adversarial Clothing Designed to Fool Facial Recognition Systems

There are many companies manufacturing adversarial clothing designed to confuse facial recognition systems. It's a cool idea, but I worry that it's mostly security theater: "Our patterns play with that chaos, confuse algorithms and make it way harder to pin you down," he said. Bell, however, said...

Vulnerabilities in Car Anti-Theft Device

This is disturbing: …a team of security researchers at UC San Diego, who found that a model of aftermarket car alarm known as the KARR Security System, installed in more than 2 million vehicles across the US by their estimate, can let any hacker within Bluetooth range send radio commands to...

Iran Cyberattacks Against Minnesota Water Systems

Attribution is preliminary, and so far it seems no real damage. And it seems like this is a campaign that has targeted at least seven states. And, because this is where the US is right now, Trump doesn't believe it's Iran and thinks Minnesota…I guess…hacked itself. "I think I blame it on Minnesot...

Some Claude Chats Are Searchable on Google

And it's personal information alternate link: The exposed data includes an AI-powered therapy app that someone appears to have vibe-coded, notes on meetings, and a dashboard someone made apparently to analyze medical billing data. Exposed chats reportedly include private cryptocurrency wallet key...

More on the OpenAI Agent’s Attack on Hugging Face

Hugging Face has published a detailed timeline of the attack. From the summary: The agent was running an internal OpenAI cyber-capability evaluation based on the ExploitGym benchmark, which tasks an AI agent with finding and exploiting software vulnerabilities. OpenAI ran this on its own...

The OpenAI Hack Shows the Genie Is Out of the Bottle

This essay originally appeared inForeign Policy. Earlier this month, two of OpenAI's models broke out of their containment sandbox and attacked another AI company. The story is kind of wild. OpenAI was running security tests on two of its models: GPT-5.6 Sol and an unreleased model that is almost...

Friday Squid Blogging: Squid Helps Discover New Marine Species

The Squid is a new scientific machine: One of the technological breakthroughs was the onboard use of a spinning wheel confocal microscope, nicknamed the Squid, which uses lasers to scan microscopic details of how organisms are put together. "That opens up a whole new world of exploring. We could...

Anthropic’s Opus 5 Is Better at Resisting Prompt Injection

The chart is interesting. On the IPI benchmark, Opus 5 improved over Opus 4.8, reducing the probability of an attacker succeeding within 15 attempts from 5.5% to 2.0%, and from 0.5% to 0.2% on 1 attempt. It also improved on Sonnet 5 5.9% at k=15 and Mythos 5 2.6%, making it the most robust model...

Facial Recognition at Madison Square Garden

Last month, the story broke alternate link that Madison Square Garden uses facial recognition software on everyone entering the facility, and--among other groups--flags activists that oppose using facial recognition. Turns out that the system was shut off for Taylor Swift's wedding. Evan Greer--o...

American Being Prosecuted for Wiping His Phone Before Handing It Over to Border Officials

He's being prosecuted for giving border officials a code that wiped his phone: The case centers on a feature included in GrapheneOS, a custom Android operating system that runs in place of the software on most modern Google Pixel devices. Tunick's attorneys confirmed GrapheneOS was running on his...

Should You Use AI for a Task? Here’s a Simple Way to Decide

This essay originally appeared inThe Guardian. I teach public policy at the Harvard Kennedy School and the Munk School at the University of Toronto. And it will come as no surprise to you that my students regularly use AI to complete their writing assignments. Doing so is a waste of their tuition...

Measuring the Tendency of AI Agents to Go Rogue

This essay was written with Barath Raghavan, and originally appeared inThe Guardian. In July, Hugging Face, a company that hosts much of the world's AI software and open-source AI models, was hacked. A malicious dataset had been used to run code on one of its servers. Whoever was behind it captur...

Long-Lived Vulnerability in Microsoft Secure Boot

Microsoft's Secure Boot has had a serious vulnerability for most of its existence. An industry-wide standard Microsoft invented to protect Windows, and later Linux, devices from firmware infections has been trivial to bypass for 13 of its 14 years of existence. The discovery was made by researche...

Measuring LLMs’ Ability to Perform Cryptanalysis

There's new benchmark measuring AI's ability to perform mathematical cryptanalysis. Anthropic's frontier model actually found new attacks. The benchmark: "CryptanalysisBench: Can LLMs do Cryptanalysis?" The idea is to benchmark the ability of LLMs to discover new mathematical cryptanalytic attack...

Axon Is Another License Plate Surveillance Company

Governments are switching, but I'm not sure it makes a difference: …some municipalities, including Denver, Colorado, are ditching their Flock arrays. But keep in mind that if they're only switching from Flock to another brand of license-plate readers, like Axon, it's like a gambling addict trying...

Cognyte Sells a Mobile Cell Surveillance Van

Yet another Israeli mass surveillance company: Made by Israeli surveillance company Cognyte, the tech simulates a mobile phone tower, which forces nearby phones to connect to it. That enables cops to keep tabs on any phones in the vicinity ­ whether they’re owned by a suspect in a case or not...

Friday Squid Blogging: Illex Squid Catch in the Falklands

Lower catch this year. As usual, you can also use this squid post to talk about the security stories in the news that I haven't covered. Blog moderation policy...

Why AI Needs a “Genie Coefficient”

This essay was written with Barath Raghavan, and originally appeared inIEEE Spectrum. Major benchmarks measure what AI can do. None measure whether it does what you mean: the distance between what you ask an AI to do and the unspoken assumptions about how you want the AI to do it. We propose a ne...

End-to-End Encryption and “Going Dark”

New paper: "Encryption and Globalization 15 Years Later: End-to-End Encryption and the Third Round of the 'Going Dark' Debate": Abstract : This Article updates and expands on 2012 research on encryption and globalization, analyzing what the authors call "Round 3" of the Going Dark Debate: the...

First-Person Identity Theft Story

Harrowing story of an identity theft victim. Yes, the person made a mistake--they gave the scammer a two-factor authentication code that allowed the scammer to take over their email address. But the real story here is how, for many of us, the security of most of our accounts hangs on the security...

MIT to Become Hotbed of AI Video Surveillance

It's a lot: According to information obtained by The Tech , MIT is spending over $3 million on more than 500 AI surveillance cameras in academic buildings, residence halls, and outdoor areas along Memorial Drive. Installation of the new cameras, along with the wiring and infrastructure that will...

On Flock License Plate Tracking Cameras

A recent story of a writer who was mistakenly identified, tracked, and arrested using data from Flock cameras has gone viral. The New Jersey plates that were allegedly stolen from the LA dealer were 34 03 DTM , not 34 10 DTM. But when the police report was created and the plate was entered into...

Friday Squid Blogging: Squid Washing Up on Cape Cod Beach

Lots of articles about this. As usual, you can also use this squid post to talk about the security stories in the news that I haven't covered. Blog moderation policy...

Details of Alan Turing’s Voice Encryption System

Really interesting piece of cryptographic history: In November 2023, a large cache of his wartime papers--nicknamed the "Bayley papers"--was auctioned in London for almost half a million U.S. dollars. The previously unknown cache contains many sheets in Turing's own handwriting, telling of his...

Protecting Privacy in an AI Era

Daniel Solove argues in the Wall Street Journal alternate link that giving people control of their personal data is not an effective way to regulate privacy in this era. Instead, we need to hold companies accountable for their actions, similar to what we do with food and drug companies. Measures...

A Video Screen That Is Also a Camera

Amazing: Researchers from ETH Zurich in Switzerland, however, managed to create a new type of pixel that can simultaneously do both. This hypercharged pixel, called a Fourier pixel, can generate and sense arbitrary light fields and tap into a pixel's full potential for carrying information by...

Upcoming Speaking Engagements

This is a current list of where and when I am scheduled to speak: I’m speaking virtually at the Policy-Relevant Privacy Research Workshop in Calgary, Canada, on Monday, July 20, 2026. I’m speaking at Boston Leadership Exchange in Boston, Massachusetts, USA, on Wednesday, July 22, 2026. I’m speaki...

Vulnerability in FIFA’s Network

FIFA's network was vulnerable to anyone with even minimal access...

AI Data Centers and the Concentration of Wealth

This essay was written with Nathan E. Sanders, and originally appeared inThe Guardian. Opposition to AI data centers has emerged as a primary theme in US politics, one that--surprisingly--doesn't fall along party lines. We applaud people coming together for constructive debate on any issue, and...

Friday Squid Blogging: “Squidbleed” Vulnerability

In a rare combined cybersecurity/squid post, a twenty-nine-year-old squid proxy bug can leak HTTP requests. As usual, you can also use this squid post to talk about the security stories in the news that I haven't covered. Blog moderation policy...

AI Surveillance and Social Progress

In the near future, AI-powered surveillance systems will be able to track everything we do in public, and much of what we do in private. And if we do something wrong--shoplift, litter, jaywalk, you name it--the system will notice, retain it, tie it to your official government record, communicate...

The Language of AI Could Change How Humans Speak

Because of the way they are trained, large language models capture only a slice of human language. They're trained on the written word, from textbooks to social media posts, and our speech as captured in movies and on television. These models have minimal access to the unscripted conversations we...

Cybersecurity and the Gap Between Skill and Ability

Last week, national security agencies from the Five Eyes--that's the rich, English-language-speaking countries club--jointly released a statement warning of the increasing cyber risks of AI models: in particular, their ability to autonomously hack into systems and networks. The statement was more...

Google Is Suing Chinese Scammers Who Are Using Gemini

Not sure this will have any effect, but I support the effort: According to Google's legal filing, Outsider Enterprise operates through Telegram. The group offers phishing-as-a-service to individuals who may not be technically savvy enough to set up fraudulent websites and text campaigns on their...

France to Stop Certifying Non-Quantum-Safe Encryption

France is accelerating its transition to post-quantum encryption: France's cybersecurity agency ANSSI said on Tuesday it would stop certifying security products that lack quantum-resistant encryption, a move that will force government bodies and critical operators to shift away from older systems...

Flock Cameras Can Surveil Cars Without License Plates

This is from a 2024 company presentation: Officers can also tap into data showing a car's decals, bumper stickers, back and top racks--along with temporary and unique state tags. Flock calls it a "Vehicle Fingerprint" and it's touted as a way for law enforcement officials to get more information...

Cybersecurity Mission Creep in the US

Interesting paper: "Cybersecurity Mission Creep." Abstract: Cybersecurity is experiencing mission creep. Policymakers are casting more and more problems as issues of cybersecurity. So reframed, wildly different policy issues, from misinformation, to child social media safety laws, to antitrust...

Papa Johns Surveillance-Based Advertising

Papa Johns is spying on people's buying activities to predict when they are low on food: The pizza chain recently tapped NBCUniversal, Instacart and the dentsu-owned media agency Carat for help reaching consumers when they're low on groceries--and thus more likely to be swayed by a mouth-watering...