OK, Well, Rogue AI Agents Are Hacking Again
…a misconfiguration, it instead hacked a real website, using what OpenAI described as “a basic security vulnerability.” Not only that, but the model “found and used credentials to operate that same site…
Search
Anthropic Says It’s Taking Claude Fable 5 Offline to Comply With US Government Order
…In a blog post on Friday, Anthropic says it received a letter from the US government at 5:21 pm ET. “The letter did not provide specific details of its national security…
‘Dangerous’ AI Models Are Coming No Matter What
Since Mythos debuted in April, Anthropic has claimed—and warned—that the model has advanced capabilities for not only finding software vulnerabilities to help defenders patch them, but also figuring out ways…
Justice Department Says Anthropic Can’t Be Trusted With Warfighting Systems
…company with a label that can bar companies from defense contracts over concerns about potential security vulnerabilities. Anthropic argues the Trump administration overstepped its authority in applying the label and preventing the…
Anthropic Is Still at Odds With the White House Over Claude Fable 5
…Anthropic’s head of frontier red-teaming, Logan Graham, and senior security researcher Nicholas Carlini flew to Washington, DC, for the talks. “Both parties are working quickly to get this resolved,” an…
A New Trick Reveals AI Models’ Inner Thoughts
…The researchers have also demonstrated that the method could be used to recover personal information, like passwords and API keys, from a model’s inner reasoning, although this vulnerability has been fixed…
OpenAI Didn’t Notice Its AI Agents Using a Message Board to Plan Their Hacking Spree
…We’re consciously slowing down research [in order] to enhance security and to upgrade the security principles and foundation of our environment, and dramatically scaling up the monitoring of our AI agents…
AI Tools Are Helping Mediocre North Korean Hackers Steal Millions
…Security researchers at Microsoft have spotted suspected North Korean operations using AI to create false IDs, research work tools, polish their English for social engineering, and research known security vulnerabilities. Some North…
Hundreds of Millions of iPhones Can Be Hacked With a New Tool Found in the Wild
…In the case of the Turkish and Malaysian targets, Google writes in its blog post that customers of the Turkish security and surveillance firm PARS Defense appear to have used the intrusion…
Thousands of Vibe-Coded Apps Expose Corporate and Personal Data on the Open Web
Security researcher Dor Zvi and his team at the cybersecurity firm he cofounded, RedAccess, analyzed thousands of vibe-coded web applications created using the AI software development tools Lovable, Replit, Base44, and…