Data Poisoning Attacks in Contextual Bandits

08/17/2018
by   Yuzhe Ma, et al.
0

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 general attack framework based on convex optimization and show that by slightly manipulating rewards in the data, an attacker can force the bandit algorithm to pull a target arm for a target contextual vector. The target arm and target contextual vector are both chosen by the attacker. That is, the attacker can hijack the behavior of a contextual bandit. We also investigate the feasibility and the side effects of such attacks, and identify future directions for defense. Experiments on both synthetic and real-world data demonstrate the efficiency of the attack algorithm.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/16/2019

Data Poisoning Attacks on Stochastic Bandits

Stochastic multi-armed bandits form a class of online learning problems ...
research
10/29/2018

Adversarial Attacks on Stochastic Bandits

We study adversarial attacks that manipulate the reward signals to contr...
research
05/29/2023

Contextual Bandits with Budgeted Information Reveal

Contextual bandit algorithms are commonly used in digital health to reco...
research
02/10/2020

Adversarial Attacks on Linear Contextual Bandits

Contextual bandit algorithms are applied in a wide range of domains, fro...
research
10/12/2022

Simulated Contextual Bandits for Personalization Tasks from Recommendation Datasets

We propose a method for generating simulated contextual bandit environme...
research
08/21/2020

Offline Contextual Multi-armed Bandits for Mobile Health Interventions: A Case Study on Emotion Regulation

Delivering treatment recommendations via pervasive electronic devices su...
research
10/20/2022

Vertical Federated Linear Contextual Bandits

In this paper, we investigate a novel problem of building contextual ban...

Please sign up or login with your details

Forgot password? Click here to reset