tml-epfl/llm-adaptive-attacks
Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]
ShellMIT
Stargazers
- afrideva
- Bai-YTUC Berkeley
- breadchrisLunaSec
- chawinsMeta
- chchch0109
- dobribanThe Wharton School, University of Pennsylvania
- dougzecPorto Alegre, Brazil
- ImKeTTSanta Cruz, CA
- jiaxiaojunQAQNanyang Technological University
- jihoontackKAIST
- JingtongSuNew York University
- kskangSeoul, South Korea
- ltroin
- MarcellusZhaoÉcole Polytechnique Fédérale de Lausanne
- max-andrEPFL
- Minami-su
- N3mes1shttps://github.com/ReaQta
- nurlanov-zhUniversity of Bonn
- P2333Sea AI Lab
- persistzShanghaiTech University
- Punkwe1ght555
- r1cc4rd0m4zz4
- radarFudanNUS
- rickyang1114Zhejiang University
- ScorpionOO8
- shannonsands
- shoaibahmedUniversity of Cambridge
- smellslikemlSmellsLikeML
- stevensypParis, France
- tunahorseDallas
- vaxilicaihouxianChina
- Xianjun-Yang
- xszheng2020
- xunguangwangHKUST
- yaodongyuUC Berkeley
- zivkar