mlsanityData to 7 Oct 2026

Data Poisoning Attacks in Contextual Bandits

arXiv 1808.05760 ↗First posted 17 Aug 2018cs.LG cs.CR stat.MLcited by 22

Not on the map. Why?

Abstract (arXiv)

We study offline data poisoning attacks in contextual bandits, a class of reinforcement learning problems with important applications in online recommendation and adaptive medical treatment, among others. We provide a general attack framework based on convex optimization and show that by slightly manipulating rewards in the data, an attacker can force the bandit algorithm to pull a target arm for a target contextual vector. The target arm and target contextual vector are both chosen by the attacker. That is, the attacker can hijack the behavior of a contextual bandit. We also investigate the feasibility and the side effects of such attacks, and identify future directions for defense. Experiments on both synthetic and real-world data demonstrate the efficiency of the attack algorithm.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 8; 2022: 4; 2023: 4; 2024: 2; 2025: 0; 2026: 3.

22 papers.

Sort:

By area:

  1. 2022Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoningcited by 93
  2. 2019Policy Poisoning in Batch Reinforcement Learning and Controlcited by 70
  3. 2021Robust Stochastic Linear Contextual Bandits Under Adversarial Attackscited by 33
  4. 2023RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Modelscited by 32
  5. 2021Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environmentscited by 26
  6. 2021Defense Against Reward Poisoning Attacks in Reinforcement Learningcited by 20
  7. 2022Reward Poisoning Attacks on Offline Multi-Agent Reinforcement Learningcited by 19
  8. 2021Accumulative Poisoning Attacks on Real-time Datacited by 10
  9. 2021When Are Linear Stochastic Bandits Attackable?cited by 10
  10. 2021Saving Stochastic Bandits from Poisoning Attacks via Limited Data Verificationcited by 9
  11. 2021Game Redesign in No-regret Game Playingcited by 8
  12. 2023Adversarial Attacks on Adversarial Banditscited by 6
10 more
  1. 2022Reward Delay Attacks on Deep Reinforcement Learningcited by 5
  2. 2021Efficient Action Poisoning Attacks on Linear Contextual Banditscited by 3
  3. 2023Online Corrupted User Detection and Regret Minimizationcited by 3
  4. 2024Stealthy Adversarial Attacks on Stochastic Multi-Armed Banditscited by 2
  5. 2026Efficient Adversarial Attacks on High-dimensional Offline Banditscited by 2
  6. 2022Security of Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 1
  7. 2024Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learningcited by 1
  8. 2023Reward Teaching for Federated Multi-armed Banditscited by 0
  9. 2026Learning to Attack: A Bandit Approach to Adversarial Context Poisoningcited by 0
  10. 2026Efficient Preference Poisoning Attack on Offline RLHFcited by 0