mlsanityData to 14 Oct 2026

Adversarial Attacks on Stochastic Bandits

arXiv 1810.12188 ↗First posted 29 Oct 2018cs.LG cs.AI cs.CRcited by 57

Not on the map. Why?

Abstract (arXiv)

We study adversarial attacks that manipulate the reward signals to control the actions chosen by a stochastic multi-armed bandit algorithm. We propose the first attack against two popular bandit algorithms: ε-greedy and UCB, without knowledge of the mean rewards. The attacker is able to spend only logarithmic effort, multiplied by a problem-specific parameter that becomes smaller as the bandit problem gets easier to attack. The result means the attacker can easily hijack the behavior of the bandit algorithm to promote or obstruct certain actions, say, a particular medical treatment. As bandits are seeing increasingly wide use in practice, our study exposes a significant security threat.

Key facts. Cited by 57 papers in the map (data through 14 Oct 2026). First posted on arXiv 29 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 16; 2022: 9; 2023: 14; 2024: 6; 2025: 7; 2026: 4.

57 papers.

Sort:

By area:

  1. 2019Policy Poisoning in Batch Reinforcement Learning and Controlcited by 70
  2. 2021Robust Stochastic Linear Contextual Bandits Under Adversarial Attackscited by 33
  3. 2021Provably Efficient Black-Box Action Poisoning Attacks Against Reinforcement Learningcited by 29
  4. 2021Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environmentscited by 26
  5. 2021Defense Against Reward Poisoning Attacks in Reinforcement Learningcited by 21
  6. 2021On Optimal Robustness to Adversarial Corruption in Online Decision Problemscited by 21
  7. 2021Linear Contextual Bandits with Adversarial Corruptionscited by 21
  8. 2022Understanding the Limits of Poisoning Attacks in Episodic Reinforcement Learningcited by 21
  9. 2021Exploiting Heterogeneity in Robust Federated Best-Arm Identificationcited by 20
  10. 2022Reward Poisoning Attacks on Offline Multi-Agent Reinforcement Learningcited by 20
  11. 2023Robust Lipschitz Bandits to Adversarial Corruptionscited by 15
  12. 2024Trustworthy Distributed AI Systems: Robustness, Privacy, and Governancecited by 14
38 more
  1. 2022Pareto Regret Analyses in Multi-objective Multi-armed Banditcited by 13
  2. 2023Best-of-Both-Worlds Algorithms for Linear Contextual Banditscited by 11
  3. 2021Accumulative Poisoning Attacks on Real-time Datacited by 10
  4. 2021When Are Linear Stochastic Bandits Attackable?cited by 10
  5. 2021Saving Stochastic Bandits from Poisoning Attacks via Limited Data Verificationcited by 9
  6. 2022Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learningcited by 9
  7. 2021Robust Bandit Learning with Imperfect Contextcited by 8
  8. 2021Game Redesign in No-regret Game Playingcited by 8
  9. 2021Combinatorial Bandits under Strategic Manipulationscited by 6
  10. 2022Federated Multi-Armed Bandits Under Byzantine Attackscited by 6
  11. 2023Adversarial Attacks on Adversarial Banditscited by 6
  12. 2023Adversarial Attacks on Online Learning to Rank with Click Feedbackcited by 6
  13. 2023Adversarial Attacks on Online Learning to Rank with Stochastic Click Modelscited by 6
  14. 2021Adversarial Attacks on Gaussian Process Banditscited by 5
  15. 2022Collaborative Linear Bandits with Adversarial Agents: Near-Optimal Regret Boundscited by 5
  16. 2022Reward Delay Attacks on Deep Reinforcement Learningcited by 5
  17. 2023Black-Box Targeted Reward Poisoning Attack Against Online Deep Reinforcement Learningcited by 5
  18. 2025Provably Efficient Multi-Objective Bandit Algorithms under Preference-Centric Customizationcited by 5
  19. 2021Best-of-All-Worlds Bounds for Online Learning with Feedback Graphscited by 4
  20. 2021Efficient Action Poisoning Attacks on Linear Contextual Banditscited by 3
  21. 2023Online Corrupted User Detection and Regret Minimizationcited by 3
  22. 2023Byzantine-Resilient Decentralized Multi-Armed Banditscited by 3
  23. 2025Practical Adversarial Attacks on Stochastic Bandits via Fake Data Injectioncited by 3
  24. 2023CRIMED: Lower and Upper Bounds on Regret for Bandits with Unbounded Stochastic Corruptioncited by 2
  25. 2023Adversarial Attacks on Combinatorial Multi-Armed Banditscited by 2
  26. 2024Stealthy Adversarial Attacks on Stochastic Multi-Armed Banditscited by 2
  27. 2024Robust Q-Learning under Corrupted Rewardscited by 2
  28. 2024Robust Thompson Sampling Algorithms Against Reward Poisoning Attackscited by 2
  29. 2025Greedy Algorithm for Structured Bandits: A Sharp Characterization of Asymptotic Success / Failurecited by 2
  30. 2026Efficient Adversarial Attacks on High-dimensional Offline Banditscited by 2
  31. 2023Corruption-Robust Lipschitz Contextual Searchcited by 1
  32. 2024Stochastic Bandits Robust to Adversarial Attackscited by 1
  33. 2024Identifying the Best Arm in the Presence of Global Environment Shiftscited by 1
  34. 2025Corruption-Tolerant Asynchronous Q-Learning with Near-Optimal Ratescited by 1
  35. 2026Efficient Preference Poisoning Attack on Offline RLHFcited by 1
  36. 2022Robust Multi-Agent Bandits Over Undirected Graphscited by 0
  37. 2022Sample Complexity of an Adversarial Attack on UCB-based Best-arm Identification Policycited by 0
  38. 2023Robust and differentially private stochastic linear banditscited by 0

50 most cited of 57 All 57 (JSON)