Friend or Foe: How LLMs' Safety Mind Gets Fooled by Intent Shift Attack

Peng Ding, Jun Kuang, Wen Sun, Zongyu Wang, Xuezhi Cao, Xunliang Cai, Jiajun Chen, Shujian Huang

Published: 2025, Last Modified: 01 Jun 2026CoRR 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Loading