How Google used AI agents to find and fix 1,072 Chrome security bugs - in 60 days
With 3.5 billion active users to protect, Google is relying on Gemini to find Chrome security bugs fast - and before attackers do.
Google employed artificial intelligence agents to identify and rectify 1,072 security flaws within the Chrome browser in a span of 60 days, as revealed by a recent blog post from the Chrome security team. This process significantly reduces the time developers typically spend on fixing bugs, which can be substantial. With Chrome being one of the most widely used browsers globally, with 3.5 billion active users, the stakes are incredibly high.
The Chrome security team's use of AI demonstrates their serious approach to safeguarding users' data and privacy.
The pace at which Google releases new versions of Chrome, typically once per month, is quite rapid. With each release, the potential for disruption worldwide is significant. Fixing a bug requires validating the bug, implementing the fix, conducting quality assurance (QA) tests to prevent conflicts with web pages and Chrome extensions, and then encouraging users to update their browsers.
The team uses a four-stage triage operation to manage this process efficiently. In the first stage, AI agents filter out irrelevant reports, duplicates, and non-security vulnerabilities. In the second stage, AI agents reproduce the identified bugs in virtual environments that mirror the browser and operating system.
Written by urgent.news from ZDNet's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
