notesum.ai

Published at November 6

MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue

cs.AI
cs.CL
cs.CR

Released Date: November 6, 2024

Authors: Fengxiang Wang1, Ranjie Duan1, Peng Xiao2, Xiaojun Jia3, YueFeng Chen1, Chongwen Wang4, Jialing Tao1, Hang Su3, Jun Zhu3, Hui Xue1

Aff.: 1Alibaba Group; 2Nanyang Technological University; 3Tsinghua University; 4Beijing Institute of Technology

Arxiv: http://arxiv.org/abs/2411.03814v1