Patch Me If You Can: AI Codemods for Secure-by-Default Android Apps

Meta's Product Security team describes their AI-powered approach to securing Android apps at scale across millions of lines of code.

• •Meta developed secure-by-default frameworks that wrap potentially unsafe Android OS APIs, making the secure path the easiest path for developers
• •Generative AI is used to automate migration of existing code to these secure frameworks at scale
• •The system can propose, validate, and submit security patches across millions of lines of code with minimal friction
• •A single vulnerability class can be replicated across hundreds of call sites in a multi-app codebase serving billions of users
• •The approach was discussed on the Meta Tech Podcast by Pascal Hartig, Alex, and Tanu from Meta's Product Security team