SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces

Documenti analoghi

• TrinityGuard: A Unified Framework for Safeguarding Multi-Agent Systems
  di: Wang, Kai, et al.
  Pubblicazione: (2026)
• Memory Poisoning Attack and Defense on Memory Based LLM-Agents
  di: Sunil, Balachandra Devarangadi, et al.
  Pubblicazione: (2026)
• Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models
  di: Ye, Rui, et al.
  Pubblicazione: (2024)
• When Embedding-Based Defenses Fail: Rethinking Safety in LLM-Based Multi-Agent Systems
  di: Zhang, Lingxi, et al.
  Pubblicazione: (2026)
• Attack the Messages, Not the Agents: A Multi-round Adaptive Stealthy Tampering Framework for LLM-MAS
  di: Yan, Bingyu, et al.
  Pubblicazione: (2025)