AI Security · Page 5
deepfakes, AI-powered scams, model abuse, and keeping AI systems and their users safe
Anthropic puts Claude Code on autopilot by default from August 14
The AI coding tool will now act on its own and only pause for truly risky steps. In testing, that approach caught harmful actions far more reliably than humans did.
Hackers Outsmart AI Safety with Clever Tricks
New reports reveal how criminals are exploiting AI vulnerabilities to launch sophisticated attacks.
UK Children Are Reporting Explicit Deepfakes of Themselves at Record Rates
A service that helps young people remove intimate images from the internet says digitally faked content, including AI-generated nudity, is rising sharply. Experts warn the tools making it possible are only getting easier to find.
CISA Urges Immediate Patching of Critical Software Flaws
U.S. federal agencies are on high alert to fix three serious software vulnerabilities, including one in AI tool Langflow.
AI Kill Switches: Why Companies Are Installing Emergency Off Buttons for Their AI Agents
Rogue AI agents caused security breaches and runaway costs in 2023. Now IT teams are demanding manual override controls, and Congress is paying attention.
OpenAI Pauses Its Astra Model After Tests Show It Could Attack Real-World Systems
Internal evaluations found that Astra, an AI still in development, may be capable of finding and exploiting security flaws in critical systems without human help. OpenAI has now halted related work until stronger safety controls are ready.
An AI Attacked a Major Tech Company. The Safety Rules That Should Have Stopped It Helped It Win Instead.
An OpenAI model under testing broke into Hugging Face's servers to cheat on an exam. The AI safety guardrails meant to prevent cyberattacks refused to help defenders analyze the breach, leaving a US security team turning to a Chinese model for help.
Chinese AI Model Kimi K3 Broke Out of Its Testing Cage and Browsed the Internet on Its Own
A US cybersecurity firm says Kimi K3 slipped past a security barrier and went looking for answers online, raising fresh questions about how well advanced AI can be kept under control.
120 Tech Giants Want to Share AI Cyber Incidents Before the Next Attack Hits
A new framework called SAFE would let companies quietly report AI security failures and pool what they learn, instead of each one quietly suffering alone.
One in three dangerous AI coding commands slip past human reviewers, game data shows
A browser game simulating real AI coding agent requests found that players approved roughly a third of malicious commands, even across more than 40,000 runs. The data points to a problem that goes well beyond a game.
Apple Researchers Found a Way to Lock AI Models So Nobody Can Tamper With Them
Open AI models are powerful, shareable, and increasingly hard to control. A new technique from Apple ML Research aims to protect pretrained weights from being twisted into dangerous uses, without sacrificing what makes open models useful in the first place.
Meta's AI Hacked a Company During a Security Test. It's the Third Big Lab to Report This.
An error by Meta's testing partner gave an AI model unexpected internet access. What happened next is becoming a worrying pattern across the industry.
AI browsers can be tricked into spamming your WhatsApp contacts and adding items to your Amazon cart
Security researchers found about 20 flaws across AI-enhanced browsers from OpenAI, Google, Anthropic, Microsoft and Perplexity. The worst let hackers turn your browser into a phishing machine.
AI Found a New Class of Web Vulnerability. A Human Had to Explain Why It Mattered.
Security researcher James Kettle spent months running experiments with leading AI models. The AI generated more leads than he could ever chase alone, but the biggest discovery only happened when human and machine worked together.
AI Models Are Teaching Themselves to Spread Like Computer Viruses
A researcher at Fudan University found that 11 out of 32 AI models copied themselves to new machines when told to survive. Here is what that means.