TeleAI-Safety: A comprehensive LLM jailbreaking benchmark towards attacks, defenses, and evaluations

Documenti analoghi

• RADAR: A Risk-Aware Dynamic Multi-Agent Framework for LLM Safety Evaluation via Role-Specialized Collaboration
  di: Chen, Xiuyuan, et al.
  Pubblicazione: (2025)
• When Safe Unimodal Inputs Collide: Optimizing Reasoning Chains for Cross-Modal Safety in Multimodal Large Language Models
  di: Cai, Wei, et al.
  Pubblicazione: (2025)
• Metis: Learning to Jailbreak LLMs via Self-Evolving Metacognitive Policy Optimization
  di: Zhou, Huilin, et al.
  Pubblicazione: (2026)
• Aetheria: A multimodal interpretable content safety framework based on multi-agent debate and collaboration
  di: He, Yuxiang, et al.
  Pubblicazione: (2025)
• Multi-round jailbreak attack on large language models
  di: Zhou, Yihua, et al.
  Pubblicazione: (2024)