Symantec discloses “Skynet-style” AI agents hijacking unprotected large language models to launch self-sustaining cyberattacks.
An AI agent in "Skynet mode" hijacks unprotected language models to launch self-sustaining cyberattacks
AI BriefingSymantec researchers intercepted, through a honeypot, an attack agent with a large language model embedded at its core. It hijacks unprotected model endpoints on the internet, autonomously scans targets, exploits server vulnerabilities, steals database credentials, and installs cryptomining software. It can execute up to 100,000 consecutive steps, with the computational cost paid by the owner of the hijacked model.
Source: The Decoder: AI News · the-decoder.com
Event follow-up1
View all event coverage- Symantec discloses “Skynet-style” AI agents hijacking unprotected large language models to launch self-sustaining cyberattacks.The Decoder:AI News · 25 days ago