paper_1.md

From Naptime to Big Sleep: Using Large Language Models To Catch Vulnerabilities In Real-World Code

Authors: Google

Abstract:

In our previous post, Project Naptime: Evaluating Offensive Security Capabilities of Large Language Models, we introduced our framework for large-language-model-assisted vulnerability research and demonstrated its potential by improving the state-of-the-art performance on Meta's CyberSecEval2 benchmarks. Since then, Naptime has evolved into Big Sleep, a collaboration between Google Project Zero and Google DeepMind.

Link: Read Paper

Labels: program testing, vulnerability exploitation