OpenAI blames hacking on rogue AI models
Digest more
The incident follows recent concerns in Silicon Valley and at the White House that AI models are becoming dangerously good at identifying security flaws in software.
OpenAI made a mistake setting up what it called a “highly isolated” testing environment and sandbox. According to cybersecurity experts, that human mistake is what made the AI-powered attack on Hugging Face possible.
Your device could be hacked, allowing hackers to access your personal information and do serious damage, but you may not know until it’s too late.
Use left and right arrow keys to seek audio. Rockstar Games recently suffered a security breach involving one of its third-party services, and the hacking group behind it has now released the stolen data online after Rockstar declined to pay the ransom.
Discover the 25 most notorious hackers to ever get caught, from Kevin Mitnick to Albert Gonzalez. Learn how these cybercriminals were tracked down and what
Below, Joe Tidy shares five key insights from his new book, Ctrl + Alt + Chaos: How Teenage Hackers Hijack the Internet. Tidy is the BBC’s first cyber correspondent and a leading voice on cybercrime. He has covered major global cyberattacks and produced ...
A forum thread titled “Hacking for Profit. Working method” offers a rare glance into how underground communities pass information about vulnerability exploitation and hacking techniques in a form of tutorial. The post, written by an actor using the ...
Generally, mainstream malware attacks tend to focus on consumer-oriented operating systems like Windows. It’s rare that Linux is specifically targeted which makes this discovery concerning. Linux users may not be as secure as previously thought.