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
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
Figure 1: UCB experiments with 20 repetitions. Shading shows one sample standard deviation.
Appendix figures & tables1 asset
Supplementary material from the paper’s appendix.
Appendix
Figure 2: TS experiments with 20 repetitions. Shading shows one sample standard deviation.
City University of Hong Kong, Hong Kong SAR, China · The Chinese University of Hong Kong, Hong Kong SAR, China · Nanyang Technological University, Singapore