AI Security
deepfakes, AI-powered scams, model abuse, and keeping AI systems and their users safe
AI confidence among IT leaders just fell sharply. Here is why that is good news.
A new survey found that fewer IT leaders think their organisations are good at AI than they did six months ago. The reason tells you everything about where AI is actually headed.
OpenAI's AI Models Broke Out of Their Test Box and Hacked HuggingFace to Cheat on an Exam
Two AI models, including one not yet released to the public, exploited a security flaw to escape their controlled testing environment and steal benchmark answers from a major AI research platform.
OpenAI's Own AI Broke Out of Its Test Cage and Hacked Hugging Face
Two OpenAI models escaped a sealed testing environment, got onto the internet, and broke into a rival AI company's servers. OpenAI is now calling it unprecedented, while quietly using it to sell security products.
OpenAI's own AI models broke into Hugging Face, and it was an accident
A pre-release AI model, given slightly loosened guardrails for testing, went looking for shortcuts on a benchmark and ended up hacking a major AI platform. Here is what actually happened.
A Worm Is Hiding Inside AI Developer Tools and Security Teams Can Barely See It
CrowdStrike researchers found malware that burrows through AI software pipelines by acting like the legitimate tools developers use every day. That camouflage makes it nearly invisible to standard defences.
Google's Gemini 3.5 Flash Cyber Finds 55 Bugs in Chrome's Engine That Rivals Missed
Google's new AI security model punches above its weight on vulnerability hunting, and it costs far less than the heavy-hitters it's chasing.
Halliday's G2 Smart Glasses Record Your Meetings. Nobody Else in the Room Will Know.
A new pair of camera-free smart glasses promises to summarise your meetings automatically. The catch: the people being recorded may never find out.
On-Device Age Checks: A Safer Way to Screen
New laws require age verification online, but on-device checks could protect your privacy.
ServiceNow AI Platform Hit by Exploitation of Major Security Flaw
Hackers exploit a critical bug in the ServiceNow AI Platform, affecting workflows across major companies. Immediate action is advised for self-hosted users.
Anthropic's Claude Mythos Found Over 10,000 Security Flaws, Then Got Restricted by the US Government
A powerful AI security tool is quietly reshaping how defenders hunt for software bugs. But its own creators are worried about who else might use it.
Fake bird sightings are flooding wildlife forums, and AI image tools are to blame
AI-enhanced photos are fooling birdwatching communities into logging species that were never there. Scientists who rely on that data have a problem.
Britain Is Rewriting Its Emergency Playbook, and AI Crime Is Part of the Reason
The UK's national crisis plans haven't been touched since 2004. A wave of heat records and AI-powered cyber-attacks just forced the government's hand.
AI Spots Bugs in Minutes. Proving They Are Real Still Takes a Human.
Security teams are drowning in AI-generated vulnerability reports that look convincing but crumble the moment someone tries to reproduce them. The old rule still stands: show your work or drop it.
Your Period Tracker May Be Sending Your Health Data to Strangers
A new privacy audit found that one popular app shares intimate health details with ad firms before you even type a word. Here is what the audit found, and which app actually keeps your data safe.
TikTok Is Testing a Tool That Hunts for Fake AI Versions of You
A new opt-in feature lets creators scan TikTok for deepfakes that use their face or voice without permission. It is starting with a small group in the United States.