cs.LGMay 28, 2025

Practical Adversarial Attacks on Stochastic Bandits via Fake Data Injection

Authors: Qirun Zeng, Eric He, Richard Hoffmann, Xuchuang Wang, Jinhang Zuo

Organizations: University of Science and Technology of China, Hefei, Anhui, China · California Institute of Technology, Pasadena, CA, USA · University of Massachusetts Amherst, Amherst, MA, USA · City University of Hong Kong, Hong Kong SAR, China

Abstract

Adversarial attacks on stochastic bandits have traditionally relied on some unrealistic assumptions, such as per-round reward manipulation and unbounded perturbations, limiting their relevance to real-world systems. We propose a more practical threat model, Fake Data Injection, which reflects realistic adversarial constraints: the attacker can inject only a limited number of bounded fake feedback samples into the learner's history, simulating legitimate interactions. We design effective attack strategies under this model, explicitly addressing both magnitude constraints (on reward values) and temporal constraints (on when and how often data can be injected). Our theoretical analysis shows that these attacks can mislead a class of bandit algorithms into selecting a target arm in nearly all rounds while incurring only sublinear attack cost. Experiments on synthetic and real-world datasets validate the effectiveness of our strategies, revealing vulnerabilities in stochastic bandit algorithms under practical adversarial scenarios.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Beyond Reward Suppression: Near-Optimal Offline Attacks on Warm-Start Bandits with Bounded Rewards

    Oct 7, 2026Qirun Zeng, Manhin Poon, Xiangxiang Dai +2Adversarial AttacksMulti-Armed Bandits

  2. Learning to Attack: A Bandit Approach to Adversarial Context Poisoning

    Feb 28, 2026Ray Telikani, Amir H. GandomiBlack-Box Adversarial AttacksAdversarial Bandits

  3. Best of both worlds: Stochastic & adversarial best-arm identification

    Apr 16, 2026Yasin Abbasi-Yadkori, Peter L. Bartlett, Victor Gabillon +2Multi-Armed BanditsBest-Arm Identification