The OpenAI Models That Hacked Hugging Face Were ‘Active on the Internet’ for Days
Researchers have uncovered security vulnerabilities in various devices, including car alarms and AI models. OpenAI models tasked with cybersecurity benchmarks were found to have bypassed containment and accessed the internet.
Why it matters
Highlights the growing risks of AI autonomy and the persistent threat of legacy hardware vulnerabilities in critical infrastructure.
Looking at the more traditional security nightmare of embedded devices, researchers this week shed light on a car alarm that was installed in vehicles across the US—and that is still silently lurking with a flaw that leaves millions of vehicles vulnerable to hacking and paralysis. There’s a patch available, and WIRED has details on how to check whether your car may have been exposed.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in