類似資料

• Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models
  著者:: Hu, Xiaomeng, 等
  出版事項: (2024)
• Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks
  著者:: Xiong, Chen, 等
  出版事項: (2024)
• Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
  著者:: Hu, Xiaomeng, 等
  出版事項: (2024)
• Steering in the Shadows: Causal Amplification for Activation Space Attacks in Large Language Models
  著者:: Xu, Zhiyuan, 等
  出版事項: (2025)
• Attention Slipping: A Mechanistic Understanding of Jailbreak Attacks and Defenses in LLMs
  著者:: Hu, Xiaomeng, 等
  出版事項: (2025)