Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning

Documenti analoghi

• Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs
  di: Yoon, Sangyeon, et al.
  Pubblicazione: (2026)
• SafeBehavior: Simulating Human-Like Multistage Reasoning to Mitigate Jailbreak Attacks in Large Language Models
  di: Zhao, Qinjian, et al.
  Pubblicazione: (2025)
• Involuntary Jailbreak: On Self-Prompting Attacks
  di: Guo, Yangyang, et al.
  Pubblicazione: (2025)
• Modality-Collaborative Low-Rank Decomposers for Few-Shot Video Domain Adaptation
  di: Wanyan, Yuyang, et al.
  Pubblicazione: (2025)
• Enhancing Heterogeneous Knowledge Graph Completion with a Novel GAT-based Approach
  di: Wei, Wanxu, et al.
  Pubblicazione: (2024)