Malicious Agent Detection for Robust Multi-Agent Collaborative Perception

Documenti analoghi

• SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents
  di: Yin, Sheng, et al.
  Pubblicazione: (2024)
• Physical Backdoor Attack can Jeopardize Driving with Vision-Large-Language Models
  di: Ni, Zhenyang, et al.
  Pubblicazione: (2024)
• SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills
  di: Hou, Yinghan, et al.
  Pubblicazione: (2026)
• CP-Guard+: A New Paradigm for Malicious Agent Detection and Defense in Collaborative Perception
  di: Hu, Senkang, et al.
  Pubblicazione: (2025)
• CP-uniGuard: A Unified, Probability-Agnostic, and Adaptive Framework for Malicious Agent Detection and Defense in Multi-Agent Embodied Perception Systems
  di: Hu, Senkang, et al.
  Pubblicazione: (2025)