mlsanityData to 14 Oct 2026

Black-Box Targeted Reward Poisoning Attack Against Online Deep Reinforcement Learning

arXiv 2305.10681 ↗First posted 18 May 2023cs.LG cs.CRcited by 5

Not on the map. Why?

Abstract (arXiv)

We propose the first black-box targeted attack against online deep reinforcement learning through reward poisoning during training time. Our attack is applicable to general environments with unknown dynamics learned by unknown algorithms and requires limited attack budgets and computational resources. We leverage a general framework and find conditions to ensure efficient attack under a general assumption of the learning algorithms. We show that our attack is optimal in our framework under the conditions. We experimentally verify that with limited budgets, our attack efficiently leads the learning agent to various target policies under a diverse set of popular DRL environments and state-of-the-art learners.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 18 of its 21 references that are in the map. First posted on arXiv 18 May 2023.

Builds on

18 of 21 references.

References · 18

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2017Deep reinforcement learning from human preferencescited by 3,912
  3. 2015Continuous control with deep reinforcement learningcited by 3,407
  4. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,745
  5. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 1,427
  6. 2015Dueling Network Architectures for Deep Reinforcement Learningcited by 785
  7. 2021Reinforcement learning based recommender systems: A surveycited by 188
  8. 2017Vulnerability of Deep Reinforcement Learning to Policy Induction Attackscited by 91
  9. 2020Adaptive Reward-Poisoning Attacks against Reinforcement Learningcited by 86
  10. 2020Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learningcited by 81
  11. 2018Adversarial Attacks on Stochastic Banditscited by 57
  12. 2019Data Poisoning Attacks on Stochastic Banditscited by 53
6 more
  1. 2020Vulnerability-Aware Poisoning Mechanism for Online RL with Unknown Dynamicscited by 38
  2. 2017Whatever Does Not Kill Deep Reinforcement Learning, Makes It Strongercited by 35
  3. 2020Adversarial Attacks on Linear Contextual Banditscited by 34
  4. 2019Snooping Attacks on Deep Reinforcement Learningcited by 17
  5. 2022Admissible Policy Teaching through Reward Designcited by 12
  6. 2022Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learningcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 0; 2026: 2.

5 papers.

  1. 2024Universal Black-Box Reward Poisoning Attack against Offline Reinforcement Learningcited by 4
  2. 2024Robust Deep Reinforcement Learning against Adversarial Behavior Manipulationcited by 2
  3. 2024Online Poisoning Attack Against Reinforcement Learning under Black-box Environmentscited by 2
  4. 2026When Can You Poison Rewards? A Tight Characterization of Reward Poisoning in Linear MDPscited by 0
  5. 2026When Critics Disagree: Adaptive Reward Poisoning Attacks in RIS-Aided Wireless Control Systemcited by 0