mlsanityData to 7 Oct 2026

Efficient Action Poisoning Attacks on Linear Contextual Bandits

arXiv 2112.05367 ↗First posted 10 Dec 2021cs.LG cs.CR math.OCcited by 3

Not on the map. Why?

Abstract (arXiv)

Contextual bandit algorithms have many applicants in a variety of scenarios. In order to develop trustworthy contextual bandit systems, understanding the impacts of various adversarial attacks on contextual bandit algorithms is essential. In this paper, we propose a new class of attacks: action poisoning attacks, where an adversary can change the action signal selected by the agent. We design action poisoning attack schemes against linear contextual bandit algorithms in both white-box and black-box settings. We further analyze the cost of the proposed attack strategies for a very popular and widely used bandit algorithm: LinUCB. We show that, in both white-box and black-box settings, the proposed attack schemes can force the LinUCB agent to pull a target arm very frequently by spending only logarithm cost.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 23 of its 36 references that are in the map. First posted on arXiv 10 Dec 2021.

Builds on

23 of 36 references.

References · 23

  1. 2013Intriguing properties of neural networkscited by 5,114
  2. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  3. 2016Universal adversarial perturbationscited by 774
  4. 2018Stochastic bandits robust to adversarial corruptionscited by 118
  5. 2017Vulnerability of Deep Reinforcement Learning to Policy Induction Attackscited by 91
  6. 2019Better Algorithms for Stochastic Bandits with Adversarial Corruptionscited by 91
  7. 2020Adaptive Reward-Poisoning Attacks against Reinforcement Learningcited by 86
  8. 2020Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learningcited by 81
  9. 2015Cascading Bandits: Learning to Rank in the Cascade Modelcited by 75
  10. 2019Policy Poisoning in Batch Reinforcement Learning and Controlcited by 70
  11. 2020Stochastic Linear Bandits Robust to Adversarial Attackscited by 65
  12. 2018Adversarial Attacks on Stochastic Banditscited by 56
11 more
  1. 2019Data Poisoning Attacks on Stochastic Banditscited by 52
  2. 2019Deceptive Reinforcement Learning Under Adversarial Manipulations on Cost Signalscited by 50
  3. 2020Vulnerability-Aware Poisoning Mechanism for Online RL with Unknown Dynamicscited by 38
  4. 2020Adversarial Attacks on Linear Contextual Banditscited by 34
  5. 2021Robust Stochastic Linear Contextual Bandits Under Adversarial Attackscited by 33
  6. 2021Provably Efficient Black-Box Action Poisoning Attacks Against Reinforcement Learningcited by 29
  7. 2021Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environmentscited by 26
  8. 2018Data Poisoning Attacks in Contextual Banditscited by 22
  9. 2019The Intrinsic Robustness of Stochastic Bandits to Strategic Manipulationcited by 15
  10. 2020Robust Stochastic Bandit Algorithms under Probabilistic Unbounded Adversarial Attackcited by 13
  11. 2020Action-Manipulation Attacks Against Stochastic Bandits: Attacks and Defensecited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 0; 2025: 0; 2026: 1.

3 papers.

  1. 2023Adversarial Attacks on Adversarial Banditscited by 6
  2. 2023Adversarial Attacks on Online Learning to Rank with Stochastic Click Modelscited by 6
  3. 2026Efficient Preference Poisoning Attack on Offline RLHFcited by 0