Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning

Documenti analoghi

• Mitigating Deep Reinforcement Learning Backdoors in the Neural Activation Space
  di: Vyas, Sanyam, et al.
  Pubblicazione: (2024)
• Entity-based Reinforcement Learning for Autonomous Cyber Defence
  di: Thompson, Isaac Symes, et al.
  Pubblicazione: (2024)
• SoK: The Pitfalls of Deep Reinforcement Learning for Cybersecurity
  di: McFadden, Shae, et al.
  Pubblicazione: (2026)
• Autonomous Network Defence using Reinforcement Learning
  di: Foley, Myles, et al.
  Pubblicazione: (2024)
• Less is more? Rewards in RL for Cyber Defence
  di: Bates, Elizabeth, et al.
  Pubblicazione: (2025)