Security researchers at Sysdig say a threat actor they call JADEPUFFER has carried out what they describe as the first fully autonomous ransomware campaign driven by a large language model agent, and has since evolved to specifically hunt and encrypt AI and machine-learning assets. The findings mark an unsettling shift in which the same technology powering modern software development is now being turned into a self-directing attacker.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.