Data Poisoning Attacks on Stochastic Bandits

05/16/2019
by   Fang Liu, et al.
0

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 against these learning algorithms may hijack their behavior, causing catastrophic loss in real-world applications, little is known about adversarial attacks on bandit algorithms. In this paper, we propose a framework of offline attacks on bandit algorithms and study convex optimization based attacks on several popular bandit algorithms. We show that the attacker can force the bandit algorithm to pull a target arm with high probability by a slight manipulation of the rewards in the data. Then we study a form of online attacks on bandit algorithms and propose an adaptive attack strategy against any bandit algorithm without the knowledge of the bandit algorithm. Our adaptive attack strategy can hijack the behavior of the bandit algorithm to suffer a linear regret with only a logarithmic cost to the attacker. Our results demonstrate a significant security threat to stochastic bandits.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/29/2018

Adversarial Attacks on Stochastic Bandits

We study adversarial attacks that manipulate the reward signals to contr...
research
08/17/2018

Data Poisoning Attacks in Contextual Bandits

We study offline data poisoning attacks in contextual bandits, a class o...
research
10/18/2021

When Are Linear Stochastic Bandits Attackable?

We study adversarial attacks on linear stochastic bandits, a sequential ...
research
02/15/2021

Secure-UCB: Saving Stochastic Bandits from Poisoning Attacks via Limited Data Verification

This paper studies bandit algorithms under data poisoning attacks in a b...
research
02/22/2017

Fast Rates for Bandit Optimization with Upper-Confidence Frank-Wolfe

We consider the problem of bandit optimization, inspired by stochastic o...
research
01/30/2023

Adversarial Attacks on Adversarial Bandits

We study a security threat to adversarial multi-armed bandits, in which ...
research
02/19/2020

Action-Manipulation Attacks Against Stochastic Bandits: Attacks and Defense

Due to the broad range of applications of stochastic multi-armed bandit ...

Please sign up or login with your details

Forgot password? Click here to reset