UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning

Ähnliche Einträge

• Angel or Demon: Investigating the Plasticity Interventions' Impact on Backdoor Threats in Deep Reinforcement Learning
  von: Ma, Oubo, et al.
  Veröffentlicht: (2026)
• Dullahan: Stealthy Backdoor Attack against Without-Label-Sharing Split Learning
  von: Pu, Yuwen, et al.
  Veröffentlicht: (2024)
• SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learning Systems
  von: Ma, Oubo, et al.
  Veröffentlicht: (2024)
• Mellivora Capensis: A Backdoor-Free Training Framework on the Poisoned Dataset without Auxiliary Data
  von: Pu, Yuwen, et al.
  Veröffentlicht: (2024)
• TooBadRL: Trigger Optimization to Boost Effectiveness of Backdoor Attacks on Deep Reinforcement Learning
  von: Zhang, Mingxuan, et al.
  Veröffentlicht: (2025)