thu-coai/JailbreakDefense_GoalPriority
[ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization
Python
Stargazers
- CelesteYimEast China Normal University
- chenxiex
- freeziyouWuhan, Hubei
- Jihuai-wpyfudan university
- nonstopforTsinghua University
- nurlanov-zhUniversity of Bonn
- shentt67Wuhan University
- tangminji
- wangruihui0429
- xszheng2020
- XuanaxxChina
- xuanyu123
- xunguangwangHKUST
- yangjunx21Tsinghua University
- YanhaoLi-CcPeking University
- YouliangYuanThe Chinese University of Hong Kong, Shenzhen