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...

Vulnerability in FIFA’s Network

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

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...

Friday Squid Blogging: Giant Squid Live in the Waters of Western Australia

Evidence of them has been found by analyzing DNA in the seawater. 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...

Friday Squid Blogging: How Squid Survived Extinction Events

Science news: Scientists have finally cracked a long-standing mystery about squid and cuttlefish evolution by analyzing newly sequenced genomes alongside global datasets. The research reveals that these bizarre, intelligent creatures likely originated deep in the ocean over 100 million years ago,...

Human Trust of AI Agents

Interesting research: "Humans expect rationality and cooperation from LLM opponents in strategic games." Abstract: As Large Language Models LLMs integrate into our social and economic interactions, we need to deepen our understanding of how humans respond to LLMs opponents in strategic settings. ...

Team Mirai and Democracy

Japan’s election last month and the rise of the country’s newest and most innovative political party, Team Mirai, illustrates the viability of a different way to do politics. In this model, technology is used to make democratic processes stronger, instead of undermining them. It is harnessed to...

Microsoft Xbox One Hacked

It's an impressive feat, over a decade after the box was released: Since reset glitching wasn't possible, Gaasedelen thought some voltage glitching could do the trick. So, instead of tinkering with the system rest pins the hacker targeted the momentary collapse of the CPU voltage rail. This was...

Proton Mail Shared User Information with the Police

404 Media has a story about Proton Mail giving subscriber data to the Swiss government, who passed the information to the FBI. It's metadata--payment information related to a particular account--but still important knowledge. This sort of thing happens, even to privacy-centric companies like Prot...

Is AI Good for Democracy?

Politicians fixate on the global race for technological supremacy between US and China. They debate geopolitical implications of chip exports, latest model releases from each country, and military applications of AI. Someday, they believe, we might see advancements in AI tip the scales in a...

Friday Squid Blogging: Squid Cartoon

I like this one. 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...

Upcoming Speaking Engagements

This is a current list of where and when I am scheduled to speak: I'm speaking at Ontario Tech University in Oshawa, Ontario, Canada, at 2 PM ET on Thursday, February 26, 2026. I’m speaking at the Personal AI Summit in Los Angeles, California, USA, on Thursday, March 5, 2026. I’m speaking at Tech...

Friday Squid Blogging: Do Squid Dream?

An exploration of the interesting question...

3D Printer Surveillance

New York is contemplating a bill that adds surveillance to 3D printers: New York’s 2026­2027 executive budget bill S.9005 / A.10005 includes language that should alarm every maker, educator, and small manufacturer in the state. Buried in Part C is a provision requiring all 3D printers sold or...

AI Coding Assistants Secretly Copying All Code to China

There's a new report about two AI coding assistants, used by 1.5 million developers, that are surreptitiously sending a copy of everything they ingest to China. Maybe avoid using them...

Telegram Hosting World’s Largest Darknet Market

Wired is reporting on Chinese darknet markets on Telegram. The ecosystem of marketplaces for Chinese-speaking crypto scammers hosted on the messaging service Telegram have now grown to be bigger than ever before, according to a new analysis from the crypto tracing firm Elliptic. Despite a brief...

AI vs. Human Drivers

Two competing arguments are making the rounds. The first is by a neurosurgeon in the New York Times. In an op-ed that honestly sounds like it was paid for by Waymo, the author calls driverless cars a "public health breakthrough": In medical research, there’s a practice of ending a study early whe...

Prompt Injection in AI Browsers

This is why AIs are not ready to be personal assistants: A new attack called 'CometJacking' exploits URL parameters to pass to Perplexity's Comet AI browser hidden instructions that allow access to sensitive data from connected services, like email and calendar. In a realistic scenario, no...

Friday Squid Blogging: “El Pulpo The Squid”

There is a new cigar named "El Pulpo The Squid." Yes, that means "The Octopus The 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...

Autonomous AI Hacking and the Future of Cybersecurity

AI agents are now hacking computers. They're getting better at all phases of cyberattacks, faster than most of us expected. They can chain together different aspects of a cyber operation, and hack autonomously, at computer speeds and scale. This is going to change everything. Over the summer,...

Digital Threat Modeling Under Authoritarianism

Today's world requires us to make complex and nuanced decisions about our digital security. Evaluating when to use a secure messaging app like Signal or WhatsApp, which passwords to store on your smartphone, or what to share on social media requires us to assess risks and make judgments...

Google Project Zero Changes Its Disclosure Policy

Google's vulnerability finding team is again pushing the envelope of responsible disclosure: Google's Project Zero team will retain its existing 90+30 policy regarding vulnerability disclosures, in which it provides vendors with 90 days before full disclosure takes place, with a 30-day period...

Microsoft SharePoint Zero-Day

Chinese hackers are exploiting a high-severity vulnerability in Microsoft SharePoint to steal data worldwide: The vulnerability, tracked as CVE-2025-53770, carries a severity rating of 9.8 out of a possible 10. It gives unauthenticated remote access to SharePoint Servers exposed to the Internet...

Iranian Blackout Affected Misinformation Campaigns

Dozens of accounts on X that promoted Scottish independence went dark during an internet blackout in Iran. Well, that's one way to identify fake accounts and misinformation campaigns...

White House Bans WhatsApp

Reuters is reporting that the White House has banned WhatsApp on all employee devices: The notice said the "Office of Cybersecurity has deemed WhatsApp a high risk to users due to the lack of transparency in how it protects user data, absence of stored data encryption, and potential security risk...

Paragon Spyware Used to Spy on European Journalists

Paragon is an Israeli spyware company, increasingly in the news now that NSO Group seems to be waning. "Graphite" is the name of its product. Citizen Lab caught it spying on multiple European journalists with a zero-click iOS exploit: On April 29, 2025, a select group of iOS users were notified b...

Google’s Advanced Protection Now on Android

Google has extended its Advanced Protection features to Android devices. It's not for everybody, but something to be considered by high-risk users. Wired article, behind a paywall...

Chinese AI Submersible

A Chinese company has developed an AI-piloted submersible that can reach speeds "similar to a destroyer or a US Navy torpedo," dive "up to 60 metres underwater," and "remain static for more than a month, like the stealth capabilities of a nuclear submarine." In case you're worried about the...

Friday Squid Blogging: Two-Man Giant Squid

The Brooklyn indie art-punk group, Two-Man Giant Squid, just released a new album. As usual, you can also use this squid post to talk about the security stories in the news that I haven't covered...

UK Demanded Apple Add a Backdoor to iCloud

Last month, the UK government demanded that Apple weaken the security of iCloud for users worldwide. On Friday, Apple took steps to comply for users in the United Kingdom. But the British law is written in a way that requires Apple to give its government access to anyone, anywhere in the world. I...

UK Is Ordering Apple to Break Its Own Encryption

The Washington Post is reporting that the UK government has served Apple with a "technical capability notice" as defined by the 2016 Investigatory Powers Act, requiring it to break the Advanced Data Protection encryption in iCloud for the benefit of law enforcement. This is a big deal, and...

New Advances in the Understanding of Prime Numbers

Really interesting research into the structure of prime numbers. Not immediately related to the cryptanalysis of prime-number-based public-key algorithms, but every little bit matters...

What Graykey Can and Can’t Unlock

This is from 404 Media: The Graykey, a phone unlocking and forensics tool that is used by law enforcement around the world, is only able to retrieve partial data from all modern iPhones that run iOS 18 or iOS 18.0.1, which are two recently released versions of Apple's mobile operating system,...

Subverting LLM Coders

Really interesting research: "An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection": Abstract : Large Language Models LLMs have transformed code completion tasks, providing context-based suggestions to boost...

Microsoft Is Adding New Cryptography Algorithms

Microsoft is updating SymCrypt, its core cryptographic library, with new quantum-secure algorithms. Microsofts details are here. From a news article: The first new algorithm Microsoft added to SymCrypt is called ML-KEM. Previously known as CRYSTALS-Kyber, ML-KEM is one of three post-quantum...

Compromising the Secure Boot Process

This isnt good: On Thursday, researchers from security firm Binarly revealed that Secure Boot is completely compromised on more than 200 device models sold by Acer, Dell, Gigabyte, Intel, and Supermicro. The cause: a cryptographic key underpinning Secure Boot on those models that was compromised ...

On the CSRB’s Non-Investigation of the SolarWinds Attack

ProPublica has a long investigative article on how the Cyber Safety Review Board failed to investigate the SolarWinds attack, and specifically Microsofts culpability, even though they were directed by President Biden to do so...

The US Is Banning Kaspersky

This move has been coming for a long time. The Biden administration on Thursday said it’s banning the company from selling its products to new US-based customers starting on July 20, with the company only allowed to provide software updates to existing customers through September 29. The ban--­th...

The Justice Department Took Down the 911 S5 Botnet

The US Justice Department has dismantled an enormous botnet: According to an indictment unsealed on May 24, from 2014 through July 2022, Wang and others are alleged to have created and disseminated malware to compromise and amass a network of millions of residential Windows computers worldwide...

AI Will Increase the Quantity—and Quality—of Phishing Scams

A piece I coauthored with Fredrik Heiding and Arun Vishwanath in the Harvard Business Review: Summary. Gen AI tools are rapidly making these emails more advanced, harder to spot, and significantly more dangerous. Recent research showed that 60% of participants fell victim to artificial intelligen...

Whale Song Code

During the Cold War, the US Navy tried to make a secret code out of whale song. The basic plan was to develop coded messages from recordings of whales, dolphins, sea lions, and seals. The submarine would broadcast the noises and a computer--the Combo Signal Recognizer CSR--would detect the specif...

LLM Prompt Injection Worm

Researchers have demonstrated a worm that spreads through prompt injection. Details: In one instance, the researchers, acting as attackers, wrote an email including the adversarial text prompt, which "poisons" the database of an email assistant using retrieval-augmented generation RAG, a way for...

Facebook’s Extensive Surveillance Network

Consumer Reports is reporting that Facebook has built a massive surveillance network: Using a panel of 709 volunteers who shared archives of their Facebook data, Consumer Reports found that a total of 186,892 companies sent data about them to the social network. On average, each participant in th...

Side Channels Are Common

Really interesting research: "Lend Me Your Ear: Passive Remote Physical Side Channels on PCs." Abstract: We show that built-in sensors in commodity PCs, such as microphones, inadvertently capture electromagnetic side-channel leakage from ongoing computation. Moreover, this information is often...

AI Bots on X (Twitter)

You can find them by searching for OpenAI chatbot warning messages, like: "Im sorry, I cannot provide a response as it goes against OpenAIs use case policy." I hadnt thought about this before: identifying bots by searching for distinctive bot phrases...

The Story of the Mirai Botnet

Over at Wired, Andy Greenberg has an excellent story about the creators of the 2016 Mirai botnet...

Friday Squid Blogging: Giant Squid from Newfoundland in the 1800s

Interesting article, with photographs. As usual, you can also use this squid post to talk about the security stories in the news that I haven’t covered. Read my blog posting guidelines here...

On IoT Devices and Software Liability

New law journal article: Smart Device Manufacturer Liability and Redress for Third-Party Cyberattack Victims Abstract: Smart devices are used to facilitate cyberattacks against both their users and third parties. While users are generally able to seek redress following a cyberattack via data...

TikTok Editorial Analysis

TikTok seems to be skewing things in the interests of the Chinese Communist Party. This is a serious analysis, and the methodology looks sound. Conclusion: Substantial Differences in Hashtag Ratios Raise Concerns about TikToks Impartiality Given the research above, we assess a strong possibility...

New Windows/Linux Firmware Attack

Interesting attack based on malicious pre-OS logo images: LogoFAIL is a constellation of two dozen newly discovered vulnerabilities that have lurked for years, if not decades, in Unified Extensible Firmware Interfaces responsible for booting modern devices that run Windows or Linux…. The...