Listen: Chrome AI Frameworks & Models

If you use Google Chrome, you might not realize that your browser is packed with machine learning models running directly on your device. These local models are designed to protect your privacy and speed up your browsing by keeping your data on your machine.

For example, specialized AI engines handle everyday tasks in the background. An engine named Anchovy processes images and extracts text, while others like Orca and Mahi handle text generation and document summaries. There are also models that run in the background to detect phishing attempts, filter out spam, predict which permissions you are likely to grant, and customize your toolbar based on how you use the web.

But as AI becomes more integrated into our browsing, it also changes how we think about security. Google points out that if a prompt tricks an AI feature into generating inappropriate content or leaking its internal instructions, it is usually not considered a security vulnerability. The browser has built-in guardrails, but simply controlling an AI's output is not a security flaw unless it causes actual, demonstrated harm to the user.

Finally, Google warns against using AI tools to find and report bugs in Chrome. These automated tools often hallucinate and submit confusing, low-quality reports that waste the security team's time. If you want to report a vulnerability, the team says human verification is still essential to ensure the issue is real, actionable, and reproducible.