Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes

Documenti analoghi

• Attention Slipping: A Mechanistic Understanding of Jailbreak Attacks and Defenses in LLMs
  di: Hu, Xiaomeng, et al.
  Pubblicazione: (2025)
• Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models
  di: Hu, Xiaomeng, et al.
  Pubblicazione: (2024)
• Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models
  di: Xiong, Chen, et al.
  Pubblicazione: (2026)
• Distract Large Language Models for Automatic Jailbreak Attack
  di: Xiao, Zeguan, et al.
  Pubblicazione: (2024)
• Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak Detection
  di: Hu, Xulin, et al.
  Pubblicazione: (2026)