Who's the Mole? Modeling and Detecting Intention-Hiding Malicious Agents in LLM-Based Multi-Agent Systems

Ähnliche Einträge

• From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration
  von: Xie, Yizhe, et al.
  Veröffentlicht: (2026)
• Secure Forgetting: A Framework for Privacy-Driven Unlearning in Large Language Model (LLM)-Based Agents
  von: Ye, Dayong, et al.
  Veröffentlicht: (2026)
• Guided Collaboration in Heterogeneous LLM-Based Multi-Agent Systems via Entropy-Based Understanding Assessment and Experience Retrieval
  von: Wang, Linlin, et al.
  Veröffentlicht: (2026)
• Towards Transparent and Incentive-Compatible Collaboration in Decentralized LLM Multi-Agent Systems: A Blockchain-Driven Approach
  von: Qi, Minfeng, et al.
  Veröffentlicht: (2025)
• INFA-Guard: Mitigating Malicious Propagation via Infection-Aware Safeguarding in LLM-Based Multi-Agent Systems
  von: Zhou, Yijin, et al.
  Veröffentlicht: (2026)