Getting to ninety-five isn’t so simple| Timothee Chauvin
Target audience: cybersecurity people, and AI / AI safety people.| Timothee Chauvin
Last updated: 2024-07-25.| Timothee Chauvin
A previous blog post introduced the eyeballvul vulnerability detection benchmark. The preprint on this work is now out (arxiv)! This post closely follows the Twitter thread where I announced this work.| Timothee Chauvin
Today I’m releasing eyeballvul, an open-source benchmark designed to enable the evaluation of SAST vulnerability detection tools, especially ones based on language models.| Timothee Chauvin
Last updated: 2024-07-05.| Timothee Chauvin
Thanks to JS Denain and Léo Grinsztajn for valuable feedback on drafts of this post.| Timothee Chauvin