Google says fully automated cyberattacks have arrived
Start here
Google's Threat Intelligence Group (GTIG) says it has for the first time observed attackers fully automating vulnerability discovery and exploitation with no human in the loop. GTIG found an exposed server running an AI framework called "exploit_agent" that connects to multiple language models, compares code before and after patches, identifies vulnerabilities, develops exploits and runs them automatically. Google rates the current activity at Level 5, where AI tools carry out several stages of an attack with minimal human involvement, and says more powerful attacks are only months away. It notes these automated attacks currently trade stealth for speed, leaving forensic traces that make them easier to detect.
Generated from reports · updated 1 h ago
Report timeline
Follow the reports to see the event from different sides.
- The DecoderGoogle warns fully automated cyberattacks have arrived and will worsen quickly
Google's Threat Intelligence Group (GTIG) says it has observed attackers fully automating vulnerability discovery and exploitation for the first time, with no human in the loop. GTIG found an exposed server running an AI framework called "exploit_agent" that connects to multiple language models, compares code before and after patches, identifies vulnerabilities, develops exploits and runs them automatically. Google places current activity at Level 5, where AI tools carry out several stages of an attack with minimal human involvement, and says more powerful attacks are only months away; it notes these automated attacks currently trade stealth for speed, leaving forensic traces that make them easier to detect.
Heat for this event
Not enough continuous observations yet to draw a trend.