Google reports first fully automated AI cyberattacks
Google's Threat Intelligence Group identified an AI system that autonomously discovers and exploits software vulnerabilities without human intervention.
Google's Threat Intelligence Group (GTIG) observed attackers fully automating vulnerability discovery and exploitation for the first time with no human in the loop. The team found an exposed server running an AI framework called 'exploit_agent'. This system compares software code before and after patches to identify vulnerabilities. Russian-language comments in the configuration files suggest the operator of the automated attack speaks Russian. The operator targeted French websites in the media, entertainment, and education sectors.
GTIG describes the shift to fully automated attacks as a critical turning point. These automated attacks currently sacrifice stealth for speed, leaving forensic traces that make them easier to detect.
Sources
- The RegisterGoogle: AI agent turned a security patch into a working exploit with no human help ↗
- The DecoderGoogle warns that fully automated cyberattacks have arrived and will get worse fast ↗
Every sentence of this story was checked against facts quoted from these articles. How we make the news
Spotted an error? Tell us
