Google Fixed More Chrome Bugs in June Than in the Past Two Years Thanks to AI
Google fixed more Chrome bugs in June than over the past two years, thanks to AI
We are leveraging Large Language Models to revolutionize how Chrome discovers, triages, and patches security vulnerabilities. By deploying AI agents at scale, we identified a sandbox escape that survived for over 13 years and fixed more bugs in recent months than in the previous two years combined. This automated approach accelerates our response to threats while maintaining rigorous safety guardrails to protect user data.
One of the bugs we found was a sandbox escape that would allow a compromised renderer to trick the browser into reading local files—a bug that quietly survived in our codebase for more than 13 years!