Efficient Action Poisoning Attacks on Linear Contextual Bandits

2021-12-10 · Guanlin Liu, Lifeng Lai

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.

📄 PDF Abstract BibTeX arXiv:2112.05367

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Armed Bandits

Learning to Attack: A Bandit Approach to Adversarial Context Poisoning

2026-02-28 · Ray Telikani, Amir H. Gandomi arxiv

Neural contextual bandits are vulnerable to adversarial attacks, where subtle perturbations to rewards, actions, or contexts induce suboptimal decisions. We introduce AdvBandit, a black-box adaptive attack that formulate…

Reinforcement Learning

Data Poisoning Attacks in Contextual Bandits

2018-08-17 · Yuzhe Ma, Kwang-Sung Jun, Lihong Li, Xiaojin Zhu

We study offline data poisoning attacks in contextual bandits, a class of reinforcement learning problems with important applications in online recommendation and adaptive medical treatment, among others. We provide a ge…

Data Poisoning Multi-Armed Bandits reinforcement-learning Reinforcement Learning+1

Data Poisoning Attacks on Stochastic Bandits

2019-05-16 · Fang Liu, Ness Shroff

Stochastic multi-armed bandits form a class of online learning problems that have important applications in online recommendation systems, adaptive medical treatment, and many others. Even though potential attacks agains…

Data Poisoning Multi-Armed Bandits Recommendation Systems

Provably Efficient Black-Box Action Poisoning Attacks Against Reinforcement Learning

2021-10-09 · NeurIPS 2021 12 · Guanlin Liu, Lifeng Lai

Due to the broad range of applications of reinforcement learning (RL), understanding the effects of adversarial attacks against RL model is essential for the safe applications of this model. Prior theoretical works on ad…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Contexts can be Cheap: Solving Stochastic Contextual Bandits with Linear Bandit Algorithms

2022-11-08 · Osama A. Hanna, Lin F. Yang, Christina Fragouli

In this paper, we address the stochastic contextual linear bandit problem, where a decision maker is provided a context (a random set of actions drawn from a distribution). The expected reward of each action is specified…