arXiv Open Access 2021

Efficient Action Poisoning Attacks on Linear Contextual Bandits

Guanlin Liu Lifeng Lai
Lihat Sumber

Abstrak

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.

Penulis (2)

G

Guanlin Liu

L

Lifeng Lai

Format Sitasi

Liu, G., Lai, L. (2021). Efficient Action Poisoning Attacks on Linear Contextual Bandits. https://arxiv.org/abs/2112.05367

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2021
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓