Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning

Documenti analoghi

• Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement Learning
  di: Liu, Shijie, et al.
  Pubblicazione: (2025)
• Enhancing the Antidote: Improved Pointwise Certifications against Poisoning Attacks
  di: Liu, Shijie, et al.
  Pubblicazione: (2023)
• Position: Certified Robustness Does Not (Yet) Imply Model Security
  di: Cullen, Andrew C., et al.
  Pubblicazione: (2025)
• Et Tu Certifications: Robustness Certificates Yield Better Adversarial Examples
  di: Cullen, Andrew C., et al.
  Pubblicazione: (2023)
• On the Bayes Inconsistency of Disagreement Discrepancy Surrogates
  di: Marchant, Neil G., et al.
  Pubblicazione: (2025)