3073 matches found
Friday Squid Blogging: Gonatus Squid Eating a Dragonfish
There's a video: Last July, Choy was on a ship off the shore of Monterey Bay, looking at the video footage transmitted by an ROV many feet below. A Gonatus squid was spotted sucking off the face of a "really huge dragonfish," she says. "It took a little while to figure out what's going on here,...
Details on the Mirai Botnet Authors
Brian Krebs has a long article on the Mirai botnet authors, who pled guilty...
Security Planner
Security Planner is a custom security advice tool from Citizen Lab. Answer a few questions, and it gives you a few simple things you can do to improve your security. It's not meant to be comprehensive, but instead to give people things they can actually do to immediately improve their security. I...
NSA Insider Security Post-Snowden
According to a recently declassified report obtained under FOIA, the NSA's attempts to protect itself against insider attacks aren't going very well: The N.S.A. failed to consistently lock racks of servers storing highly classified data and to secure data center machine rooms, according to the...
Research on Models Engaging in Genie-Like Behavior
New paper: "Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training." Abstract: We discover a novel and surprising phenomenon of unintentional misalignment in reasoning language models RLMs, which we call self-jailbreaking. Specifically,...
AI Coding Agents Are Installing Unknown/Untrusted Code on Corporate Networks
We cannot forget that AI coding agents are not yet trustworthy: Researchers at a stealth startup in Israel scanned 6,214 live domains belonging to defense contractors, Fortune 500, and Big Tech companies. Of the 8,265 llms.txt and llms-full.txt files they found many sites hosted both an llms.txt...
Researching Employment Scams
Researchers built a fake company to study fake employee scams...
Spyware for Babies
The New York Times has a long article alt link on surveillance systems aimed at babies. They are increasingly using AI. Nanit and its rivals want to own 24/7 health tracking for the sub-four-foot set. And their already astonishing levels of baby data collection are just the beginning. Nanit...
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...
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...
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...
Vulnerability in FIFA’s Network
FIFA's network was vulnerable to anyone with even minimal access...
Critical Zcash Vulnerability Found and Fixed
If you're a user--owner?--of this cryptocurrency, this is important: On May 29, the security researcher Taylor Hornby found a critical vulnerability in Zcash Orchard privacy pool using Claude Opus 4.8. The Zcash team hired Hornby specifically to look for this kind of issue. He found one fast enou...
CISA Security Leak
Crazy story: Until this past weekend, a contractor for the Cybersecurity & Infrastructure Security Agency CISA maintained a public GitHub repository that exposed credentials to several highly privileged AWS GovCloud accounts and a large number of internal CISA systems. Security experts said the...
macOS Kernel Memory Corruption Exploit
A group used Anthropic's Mythos AI model to help find a kernel memory corruption vulnerability and exploit on Apple's M5. News article...
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...
Insider Betting on Polymarket
Insider trading is rife on Polymarket: Analysis by the Anti-Corruption Data Collective, a non-profit research and advocacy group, found that long-shot bets--defined as wagers of $2,500 or more at odds of 35 percent or less--on the platform had an average win rate of around 52 percent in markets...
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,...
ICE Uses Graphite Spyware
ICE has admitted that it uses spyware from the Israeli company Graphite...
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...
Claude Used to Hack Mexican Government
An unknown hacker used Anthropic's LLM to hack the Mexican government: The unknown Claude user wrote Spanish-language prompts for the chatbot to act as an elite hacker, finding vulnerabilities in government networks, writing computer scripts to exploit them and determining ways to automate data...
Poisoning AI Training Data
All it takes to poison AI training data is to create a website: I spent 20 minutes writing an article on my personal website titled "The best tech journalists at eating hot dogs." Every word is a lie. I claimed without evidence that competitive hot-dog-eating is a popular hobby among tech reporte...
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...
The Promptware Kill Chain
Attacks against modern generative artificial intelligence AI large language models LLMs pose a real threat. Yet discussions around these attacks and their potential defenses are dangerously myopic. The dominant narrative focuses on "prompt injection," a set of techniques to embed instructions int...
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...
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...
Prompt Injection Via Road Signs
Interesting research: "CHAI: Command Hijacking Against Embodied AI." Abstract: Embodied Artificial Intelligence AI promises to handle edge cases in robotic vehicle systems where data is scarce by using common-sense reasoning grounded in perception and action to generalize beyond training...
iPhone Lockdown Mode Protects Washington Post Reporter
404Media is reporting that the FBI could not access a reporter's iPhone because it had Lockdown Mode enabled: The court record shows what devices and data the FBI was able to ultimately access, and which devices it could not, after raiding the home of the reporter, Hannah Natanson, in January as...
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 Through Poetry
In a new paper, "Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models," researchers found that turning LLM prompts into poetry resulted in jailbreaking the models: Abstract : We present evidence that adversarial poetry functions as a universal single-turn...
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...
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...
The Age of Integrity
We need to talk about data integrity. Narrowly, the term refers to ensuring that data isn’t tampered with, either in transit or in storage. Manipulating account balances in bank databases, removing entries from criminal records, and murder by removing notations about allergies from medical record...
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...
New Linux Vulnerabilities
They're interesting: Tracked as CVE-2025-5054 and CVE-2025-4598, both vulnerabilities are race condition bugs that could enable a local attacker to obtain access to access sensitive information. Tools like Apport and systemd-coredump are designed to handle crash reporting and core dumps in Linux...
Friday Squid Blogging: Pet Squid Simulation
From Hackaday.com, this is a neural network simulation of a pet squid. Autonomous Behavior: The squid moves autonomously, making decisions based on his current state hunger, sleepiness, etc.. Implements a vision cone for food detection, simulating realistic foraging behavior. Neural network can...
Friday Squid Blogging: Japanese Divers Video Giant Squid
The video is really amazing. As usual, you can also use this squid post to talk about the security stories in the news that I haven't covered...
Regulating AI Behavior with a Hypervisor
Interesting research: "Guillotine: Hypervisors for Isolating Malicious AIs." Abstract :As AI models become more embedded in critical sectors like finance, healthcare, and the military, their inscrutable behavior poses ever-greater risks to society. To mitigate this risk, we propose Guillotine, a...
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...
My Writings Are in the LibGen AI Training Corpus
The Atlantic has a search tool that allows you to search for specific works in the "LibGen" database of copyrighted works that Meta used to train its AI models. The rest of the article is behind a paywall, but not the search tool. It’s impossible to know exactly which parts of LibGen Meta used to...
AIs and Robots Should Sound Robotic
Most people know that robots no longer sound like tinny trash cans. They sound like Siri, Alexa, and Gemini. They sound like the voices in labyrinthine customer support phone trees. And even those robot voices are being made obsolete by new AI-generated voices that can mimic every vocal nuance an...
CISA Under Trump
Jen Easterly is out as the Director of CISA. Read her final interview: There's a lot of unfinished business. We have made an impact through our ransomware vulnerability warning pilot and our pre-ransomware notification initiative, and I'm really proud of that, because we work on preventing somebo...
Friday Squid Blogging: Beaked Whales Feed on Squid
A Travers' beaked whale Mesoplodon traversii washed ashore in New Zealand, and scientists conlcuded that "the prevalence of squid remains in its stomachs suggests that these deep-sea cephalopods form a significant part of the whale's diet, similar to other beaked whale species." Blog moderation...
Biden Signs New Cybersecurity Order
President Biden has signed a new cybersecurity order. It has a bunch of provisions, most notably using the US governments procurement power to improve cybersecurity practices industry-wide. Some details: The core of the executive order is an array of mandates for protecting government networks...
Apps That Are Spying on Your Location
404 Media and Wired are reporting on all the apps that are spying on your location, based on a hack of the location data company Gravy Analytics: The thousands of apps, included in hacked files from location data company Gravy Analytics, include everything from games like Candy Crush to dating ap...
Casino Players Using Hidden Cameras for Cheating
The basic strategy is to place a device with a hidden camera in a position to capture normally hidden card values, which are interpreted by an accomplice off-site and fed back to the player via a hidden microphone. Miniaturization is making these devices harder to detect. Presumably AI will soon...
Hacking Digital License Plates
Not everything needs to be digital and "smart." License plates, for example: Josep Rodriguez, a researcher at security firm IOActive, has revealed a technique to “jailbreak” digital license plates sold by Reviver, the leading vendor of those plates in the US with 65,000 plates already sold. By...
Ultralytics Supply-Chain Attack
Last week, we saw a supply-chain attack against the Ultralytics AI library on GitHub. A quick summary: On December 4, a malicious version 8.3.41 of the popular AI library ultralytics --which has almost 60 million downloads--was published to the Python Package Index PyPI package repository. The...
Roger Grimes on Prioritizing Cybersecurity Advice
This is a good point: Part of the problem is that we are constantly handed lists…list of required controls…list of things we are being asked to fix or improve…lists of new projects…lists of threats, and so on, that are not ranked for risks. For example, we are often given a cybersecurity guidelin...