Data Poisoning Attacks in Contextual Bandits
arXiv:1808.05760
Abstract
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.
arXiv commentGameSec 2018
References in corpus (6)
- A Contextual-Bandit Approach to Personalized News Article Recommendation
- Poisoning Attacks against Support Vector Machines
- Algorithms for multi-armed bandit problems
- Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning
- An Overview of Machine Teaching
- Making Contextual Decisions with Low Technical Debt