Attackers have used artificial intelligence to find software flaws and exploit them with no human involved, Google said Monday. The company says it is the first time it has seen this. The finding appears in the latest AI threat report from the Google Threat Intelligence Group (GTIG) and Mandiant.
How did attackers use AI to turn patches into exploits?
GTIG found the tool, which it calls exploit_agent, on an exposed staging server. The tool works with several frontier and locally run AI models. It compares the code of popular web software before and after each patch, spots likely flaws, then writes exploits and runs them on its own.
In the previous edition of the quarterly report, released two months earlier, GTIG said it had not seen fully autonomous attack pipelines used against targets, SiliconANGLE reported.
The server also held data stolen from victims. It contained scripts for brute-forcing passwords, installing webshells and removing rival attackers’ webshells. A configuration file carried comments in Russian. Victim data suggests the operator was targeting French media, entertainment and education websites, GTIG said.
From patch to exploit
Why are patched flaws easier targets for AI?
Patched flaws may be easier targets for AI than unknown ones, Google said. Attackers can study a finite set of material: old and new code, release notes and public research.
The company pointed to two flaws in PaperCut print servers that attackers chained together in late August. Researchers and the security firm Huntress used AI to build working exploits within a day of disclosure. Four days after disclosure, an attacker likely used AI to run a campaign against hundreds of organizations, according to GreyNoise.
After PHP flaws were patched in October, hundreds of proof-of-concept exploits appeared that did not work. AI likely produced many of them, the report says.
Open-source frameworks in the wild
Are AI-built hacking frameworks already used in live attacks?
Several groups now use open-source AI hacking frameworks in live attacks, GTIG said. They include financially motivated gangs and suspected Chinese spy groups. GTIG saw the CAIRN framework used against targets including the U.S. aerospace sector.
These tools are noisy and leave traces that make them easier to spot, Google said. But it expects attackers to rely less on humans and become stealthier as the tools improve.
“We believe it is highly likely that threat actors will continue to use these frameworks in campaigns targeting organizations globally,” GTIG wrote.
The report also describes attackers who steal cloud and AI credentials to run models on victims’ accounts. In some cases, the fraudulent charges topped $100,000 in a single day. One attack used a flaw in the LiteLLM gateway. A suspected North Korean group changed Claude Code settings files inside companies so that each launch downloaded a backdoor.
Google says it disabled the accounts and assets linked to misuse of its Gemini models.
Cet article a été rédigé avec l'assistance de l'IA.
News Factory APP - actualités agentiques pour booster votre SEO et AEO.