Google detects the first cyberattack carried out entirely by artificial intelligence
The Google Threat Intelligence Group (GTIG), together with Mandiant's incident response team, reported the first cyberattack executed end to end by artificial intelligence, with no human intervention at any stage. The attackers, Russian-speaking according to the technical attribution, used an agent system called "exploit_agent" that compared program code before and after its patches, identified exposed flaws and automatically developed the tools to exploit them. The targets were French websites in the media, entertainment and education sectors.
In 35 seconds
- Google and Mandiant reported the first attack in which AI handled every stage, with no human intervention.
- The "exploit_agent" system compared code before and after patches, found flaws and built the tools to exploit them.
- The targets were French websites in the media, entertainment and education sectors.
IASummary generated by artificial intelligence from a story by Minuto 30. It may contain errors: the original source prevails.





Comments
Be respectful. Comments reported by several people are hidden until a moderator reviews them.
You do not need an account to read, only to comment. Sign in with a code sent to your email or with your Google account. We only show the name you choose, never your email.