Stealthy Adversarial Attacks on Stochastic Multi-Armed Bandits
Not on the map. Why?
Abstract (arXiv)
Adversarial attacks against stochastic multi-armed bandit (MAB) algorithms have been extensively studied in the literature. In this work, we focus on reward poisoning attacks and find most existing attacks can be easily detected by our proposed detection method based on the test of homogeneity, due to their aggressive nature in reward manipulations. This motivates us to study the notion of stealthy attack against stochastic MABs and investigate the resulting attackability. Our analysis shows that against two popularly employed MAB algorithms, UCB1 and ε-greedy, the success of a stealthy attack depends on the environmental conditions and the realized reward of the arm pulled in the first round. We also analyze the situation for general MAB algorithms equipped with our attack detection method and find that it is possible to have a stealthy attack that almost always succeeds. This brings new insights into the security risks of MAB algorithms.
Key facts. Cited by 2 papers in the map (data through 13 Oct 2026). Builds on 20 of its 25 references that are in the map. First posted on arXiv 21 Feb 2024.
Builds on
20 of 25 references.
References · 20
- 2018Stochastic bandits robust to adversarial corruptionscited by 118
- 2017Vulnerability of Deep Reinforcement Learning to Policy Induction Attackscited by 91
- 2019Better Algorithms for Stochastic Bandits with Adversarial Corruptionscited by 91
- 2020Adaptive Reward-Poisoning Attacks against Reinforcement Learningcited by 86
- 2019Policy Poisoning in Batch Reinforcement Learning and Controlcited by 70
- 2020Stochastic Linear Bandits Robust to Adversarial Attackscited by 65
- 2018Adversarial Attacks on Stochastic Banditscited by 56
- 2019Data Poisoning Attacks on Stochastic Banditscited by 53
- 2019Deceptive Reinforcement Learning Under Adversarial Manipulations on Cost Signalscited by 50
- 2020Vulnerability-Aware Poisoning Mechanism for Online RL with Unknown Dynamicscited by 38
- 2020Adversarial Attacks on Linear Contextual Banditscited by 34
- 2021Robust Stochastic Linear Contextual Bandits Under Adversarial Attackscited by 33
8 more
- 2021Provably Efficient Black-Box Action Poisoning Attacks Against Reinforcement Learningcited by 29
- 2018Data Poisoning Attacks in Contextual Banditscited by 23
- 2019The Intrinsic Robustness of Stochastic Bandits to Strategic Manipulationcited by 15
- 2020Robust Stochastic Bandit Algorithms under Probabilistic Unbounded Adversarial Attackcited by 13
- 2021When Are Linear Stochastic Bandits Attackable?cited by 10
- 2020Action-Manipulation Attacks Against Stochastic Bandits: Attacks and Defensecited by 8
- 2023Adversarial Attacks on Online Learning to Rank with Stochastic Click Modelscited by 6
- 2023Adversarial Attacks on Combinatorial Multi-Armed Banditscited by 2
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.