This work was produced in collaboration with @jplhughes @sprice354_ @rylanschaeffer.bsky.social @FazlBarez @sanmikoyejo @sleight_henry @erikjones313 @EthanJPerez @MrinankSharma
December 13, 2024 at 5:27 PM
This work was produced in collaboration with @jplhughes @sprice354_ @rylanschaeffer.bsky.social @FazlBarez @sanmikoyejo @sleight_henry @erikjones313 @EthanJPerez @MrinankSharma
Paper: arxiv.org/abs/2412.03556
Code: github.com/jplhughes/bo...
Example jailbreaks and more: jplhughes.github.io/bon-jailbrea...
Best-of-N Jailbreaking
We introduce Best-of-N (BoN) Jailbreaking, a simple black-box algorithm that jailbreaks frontier AI systems across modalities. BoN Jailbreaking works by repeatedly sampling variations of a prompt with...
arxiv.org
December 13, 2024 at 5:27 PM
Paper: arxiv.org/abs/2412.03556
Code: github.com/jplhughes/bo...
Example jailbreaks and more: jplhughes.github.io/bon-jailbrea...