Stronger with every update: How we’re making Chrome and the web safer in the AI Era
Chrome
Stronger with every update: How we’re making Chrome and the web safer in the AI Era
Jul 30, 2026
x.com
Copy link
How Chrome is using AI to improve vulnerability discovery, triage, and patching.
Chrome Security Team
Share
x.com
Copy link
We’re living through a massive shift in the software security industry. Large Language Models (LLMs) are unlocking unprecedented capabilities for automated vulnerability discovery, scaling far beyond the limits of human security expertise, and requiring new approaches for staying ahead of attackers.<br>This means deploying AI models at scale to find and fix hundreds of security bugs, faster than ever, with the goal of achieving greater resilience and comprehensive remediation.<br>Here’s how we’re doing it.<br>The Life of A Bug<br>Some software bugs have security implications. While a purely functional bug might result in a frustrating UI freeze, a security bug (or vulnerability) can be used to build an exploit. Exploits allow attackers to perform malicious actions on a victim’s computer, such as reading private data, or controlling their machine without their knowledge.<br>Once a security bug enters the codebase, its life cycle proceeds as follows:<br>The bug is found.<br>The bug is triaged.<br>The bug is fixed.<br>A new update of Chrome with the bug fix is released.<br>Chrome is restarted and the update is applied.
Our goal is for every one of these steps to happen as quickly as possible.<br>Finding vulnerabilities<br>The Chrome Security team has been using LLMs for years. In 2023 we developed ways to use LLMs to increase security fuzzing coverage and performance. In 2024, we worked with Project Zero on Naptime, giving LLMs specialized tools for vulnerability research. And in 2025, we collaborated with DeepMind and Project Zero on Big Sleep, an AI vulnerability discovery agent that successfully found bugs in the V8 JavaScript engine and graphics stack.<br>In early 2026, we built an agent harness that used Gemini to find vulnerabilities across the broader Chrome codebase with higher efficiency and lower false positives. 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! For many of us, this moment cemented the potential of AI-powered vulnerability detection.<br>From there, we improved on our vulnerability finding agent harness by:<br>Adding support for model interoperability to leverage the unique strengths of both open-weights and proprietary models.<br>Building a knowledge base of Chrome, including all previously identified CVEs and Chrome’s entire Git history, to extend the LLMs reasoning capacity past its training data.<br>Encouraging developers to add SECURITY.md files, which help models better understand trust boundaries and develop an accurate view of the threat model.<br>Adding a “critic” agent with a separate context to consume these SECURITY.md files.<br>Introducing the ability to run vulnerability finding models over the codebase multiple times to account for model non-determinism and model improvements over time.<br>We’ve built all of this with safety in mind, and have put in place guardrails to mitigate the risk of AI behaving unexpectedly. Our AI analyzes source code strictly at rest, operating on locked-down machines that lack general internet access. We also utilize a dedicated setup for these internal scans that intercepts all network requests, employing strict allowlists based on the initiating application and destination, blocking any suspicious model activity. Furthermore, we never run models in an unrestricted mode, and we strictly limit our subagents from modifying the local system or accessing files outside of designated source code directories.<br>AI-powered vulnerability detection complements our existing security testing infrastructure. For example, fuzzing continues to be especially effective at finding bugs that arise from long-range interactions between disparate parts of our codebase, or those requiring a combination of seemingly unrelated operations.<br>We also want to continue to reward external researchers for their expertise and creativity in finding the most challenging and impactful vulnerabilities via the Chrome Vulnerability Reward Program (VRP). In early 2026, we saw a gradual increase in all categories of bug reports, but by March, the shift was apparent: we received more bug reports than we had in the entirety of 2025. This led us to change our VRP to focus researchers on bug submissions that are additive to what we are finding internally, and easily ingestible by our newly automated processing pipelines.<br>Triaging vulnerabilities<br>As we discover more security vulnerabilities with AI-powered tools, we’ve simultaneously used AI to scale and automate validating, triaging, and fixing bugs....