CS-GBA: A Critical Sample-based Gradient-guided Backdoor Attack for Offline Reinforcement Learning

Documenti analoghi

• Optimal Perturbation Budget Allocation for Data Poisoning in Offline Reinforcement Learning
  di: Qiu, Junnan, et al.
  Pubblicazione: (2025)
• Offline Reinforcement Learning with Imbalanced Datasets
  di: Jiang, Li, et al.
  Pubblicazione: (2023)
• BAPFL: Exploring Backdoor Attacks Against Prototype-based Federated Learning
  di: Zeng, Honghong, et al.
  Pubblicazione: (2025)
• BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets
  di: Gong, Chen, et al.
  Pubblicazione: (2022)
• Sample-Efficient Policy Constraint Offline Deep Reinforcement Learning based on Sample Filtering
  di: Chen, Yuanhao, et al.
  Pubblicazione: (2025)