Efficient Action Poisoning Attacks on Linear Contextual Bandits [article]

Guanlin Liu, Lifeng Lai
2021 arXiv   pre-print
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
more » ... 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.
arXiv:2112.05367v1 fatcat:3frbcvuz3za7pisisqnsyvpz4u