Ítems similars

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