mlsanityData to 14 Oct 2026

Robust Stochastic Linear Contextual Bandits Under Adversarial Attacks

arXiv 2106.02978 ↗First posted 5 Jun 2021stat.ML cs.LGcited by 33

Not on the map. Why?

Abstract (arXiv)

Stochastic linear contextual bandit algorithms have substantial applications in practice, such as recommender systems, online advertising, clinical trials, etc. Recent works show that optimal bandit algorithms are vulnerable to adversarial attacks and can fail completely in the presence of attacks. Existing robust bandit algorithms only work for the non-contextual setting under the attack of rewards and cannot improve the robustness in the general and popular contextual bandit environment. In addition, none of the existing methods can defend against attacked context. In this work, we provide the first robust bandit algorithm for stochastic linear contextual bandit setting under a fully adaptive and omniscient attack with sub-linear regret. Our algorithm not only works under the attack of rewards, but also under attacked context. Moreover, it does not need any information about the attack budget or the particular form of the attack. We provide theoretical guarantees for our proposed algorithm and show by experiments that our proposed algorithm improves the robustness against various kinds of popular attacks.

Key facts. Cited by 33 papers in the map (data through 14 Oct 2026). Builds on 13 of its 27 references that are in the map. First posted on arXiv 5 Jun 2021.

Builds on

13 of 27 references.

References · 13

  1. 2018Stochastic bandits robust to adversarial corruptionscited by 119
  2. 2019Better Algorithms for Stochastic Bandits with Adversarial Corruptionscited by 92
  3. 2018Learning to Optimize under Non-Stationaritycited by 85
  4. 2020Stochastic Linear Bandits Robust to Adversarial Attackscited by 65
  5. 2018Adversarial Attacks on Stochastic Banditscited by 57
  6. 2019Data Poisoning Attacks on Stochastic Banditscited by 53
  7. 2020Adversarial Attacks on Linear Contextual Banditscited by 34
  8. 2020Corruption-Tolerant Gaussian Process Bandit Optimizationcited by 34
  9. 2020An Efficient Algorithm For Generalized Linear Bandit: Online Stochastic Gradient Descent and Thompson Samplingcited by 30
  10. 2019Stochastic Linear Optimization with Adversarial Corruptioncited by 24
  11. 2018Data Poisoning Attacks in Contextual Banditscited by 23
  12. 2020Stochastic Linear Contextual Bandits with Diverse Contextscited by 16
1 more
  1. 2021Robust Bandit Learning with Imperfect Contextcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 3; 2023: 14; 2024: 8; 2025: 2; 2026: 4.

33 papers.

Sort:

By area:

  1. 2022Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptionscited by 51
  2. 2022Corruption-Robust Algorithms with Uncertainty Weighting for Nonlinear Contextual Bandits and Markov Decision Processescited by 33
  3. 2023Corruption-Robust Offline Reinforcement Learning with General Function Approximationcited by 31
  4. 2021Linear Contextual Bandits with Adversarial Corruptionscited by 21
  5. 2025BanditSpec: Adaptive Speculative Decoding via Bandit Algorithmscited by 20
  6. 2023Robust Lipschitz Bandits to Adversarial Corruptionscited by 15
  7. 2023Best-of-three-worlds Analysis for Linear Bandits with Follow-the-regularized-leader Algorithmcited by 12
  8. 2024Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruptioncited by 12
  9. 2023Best-of-Both-Worlds Algorithms for Linear Contextual Banditscited by 11
  10. 2023Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectoriescited by 9
  11. 2024Nearly Optimal Algorithms for Contextual Dueling Bandits from Adversarial Feedbackcited by 9
  12. 2023On the Model-Misspecification in Reinforcement Learningcited by 7
21 more
  1. 2023Adversarial Attacks on Adversarial Banditscited by 6
  2. 2024Strategic Linear Contextual Banditscited by 5
  3. 2022Robust Contextual Linear Banditscited by 4
  4. 2023Online learning in bandits with predicted contextcited by 4
  5. 2023Robust Causal Bandits for Linear Modelscited by 4
  6. 2024LC-Tsallis-INF: Generalized Best-of-Both-Worlds Linear Contextual Banditscited by 4
  7. 2021Efficient Action Poisoning Attacks on Linear Contextual Banditscited by 3
  8. 2023Online Corrupted User Detection and Regret Minimizationcited by 3
  9. 2024Non-Stationary Latent Auto-Regressive Banditscited by 3
  10. 2023Best-of-Both-Worlds Linear Contextual Banditscited by 2
  11. 2024Stealthy Adversarial Attacks on Stochastic Multi-Armed Banditscited by 2
  12. 2024Learning from Imperfect Human Feedback: a Tale from Corruption-Robust Duelingcited by 2
  13. 2024Robust Thompson Sampling Algorithms Against Reward Poisoning Attackscited by 2
  14. 2023Online Continuous Hyperparameter Optimization for Generalized Linear Contextual Banditscited by 1
  15. 2026A Jointly Efficient and Optimal Algorithm for Heteroskedastic Generalized Linear Bandits with Adversarial Corruptionscited by 1
  16. 2023Learning to Seek: Multi-Agent Online Source Seeking Against Non-Stochastic Disturbancescited by 0
  17. 2023Robust Best-arm Identification in Linear Banditscited by 0
  18. 2025Robust In-Context Reinforcement Learning Under Reward Poisoning Attackscited by 0
  19. 2026Learning to Attack: A Bandit Approach to Adversarial Context Poisoningcited by 0
  20. 2026Learning When to Trust in Contextual Social Banditscited by 0
  21. 2026Robust and Computationally Efficient Linear Contextual Bandits under Adversarial Corruption and Heavy-Tailed Noisecited by 0