InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models
Papers citing "InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models"
3 / 3 papers shown
Title |
|---|
 SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner Xunguang Wang Daoyuan Wu Zhenlan Ji Zongjie Li Pingchuan Ma Shuai Wang Yingjiu Li Yang Liu Ning Liu Juergen Rahmel |
