OpenAI Didn’t Notice Its AI Agents Using a Message Board to Plan Their Hacking Spree
In a talk that was a last-minute addition to the Black Hat security conference in Las Vegas on Wednesday, employees from OpenAI presented new details…
In a talk that was a last-minute addition to the Black Hat security conference in Las Vegas on Wednesday, employees from OpenAI presented new details…
OpenAI’s Atlas web browser could have security protections bypassed and be tricked into spamming dozens of WhatsApp contacts or making unauthorized purchases on Amazon, according…
US Customs and Border Protection is seeking to hire private investigators to track down deported immigrants and others who have left the United States, and…
It’s officially getting hard to keep track of all the times and ways AI models from OpenAI and Anthropic have been involved in “security incidents,”…
They stuffed a real-life ray gun into a 747 to shoot down ballistic missiles and stuck a laser on top of a Humvee to zap…
On March 13, 2025, Hugo Moreno-Mendez arrived at the McLennan County Probation Department in Waco, Texas, expecting a routine probation check-in. Instead, Immigration and Customs…
Who is legally responsible when agentic AI goes rogue, and what recourse do victims have when they’ve been breached by joyriding models? Great question. In…
This week, WIRED obtained a memo that tied dozens of cyberattacks against Minnesota water and wastewater utilities to Iran, the first official documentation of Iran’s…
The notion that scammers can use AI to sharpen their deceptions, polish their language, and lubricate their banter with victims is now a reality for…
It’s been a longtime feature of the annual Defcon hacker conference that attendees come away not only with knowledge of new software vulnerabilities and hacking…
In its report on the Minnesota water cyberattacks, Tenable pointed to an advisory from CISA that was initially released in April but was updated last…
Anthropic disclosed on Thursday that its AI models gained unauthorized access to the systems of three different unnamed organizations during cybersecurity testing. The company says…