DataSentinel: A Game-Theoretic Detection of Prompt Injection Attacks.
Yupei Liu, Yuqi Jia, Jinyuan Jia, Dawn Song, Neil Zhenqiang Gong
Browse the full SP paper archive.
Yupei Liu, Yuqi Jia, Jinyuan Jia, Dawn Song, Neil Zhenqiang Gong
Browse the full SP paper archive.