MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety

Documenti analoghi

• SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks
  di: Feng, Mingqian, et al.
  Pubblicazione: (2026)
• SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks
  di: Cao, Hongye, et al.
  Pubblicazione: (2025)
• Foot-In-The-Door: A Multi-turn Jailbreak for LLMs
  di: Weng, Zixuan, et al.
  Pubblicazione: (2025)
• AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents
  di: Ma, Chang, et al.
  Pubblicazione: (2024)
• Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities
  di: Sun, Chung-En, et al.
  Pubblicazione: (2024)