BigSleep

Big Sleep: Google Project Zero and DeepMind's agentic AI system for autonomous software vulnerability research using Large Language Models (LLMs).

Big Sleep is an advanced AI agent developed by Google Project Zero and DeepMind to automate and accelerate vulnerability research: a significant evolution of their 'Project Naptime.' The system uses a Large Language Model (LLM) to mimic a human security researcher's workflow, focusing on finding variants of existing security flaws. In its first real-world test, Big Sleep successfully discovered an exploitable stack buffer underflow in SQLite, a widely used open-source database engine, before the buggy code was officially released. This breakthrough demonstrates the potential for AI to provide an asymmetric advantage for defenders, finding complex memory-safety issues that traditional methods (like fuzzing) often miss.

https://googleprojectzero.blogspot.com/2024/11/from-naptime-to-big-sleep-using-large-language-models-to-catch-vulnerabilities-in-real-world-code.html