Timezone: »

Adversarial Attacks on Stochastic Bandits
Kwang-Sung Jun · Lihong Li · Yuzhe Ma · Jerry Zhu

Tue Dec 04 02:00 PM -- 04:00 PM (PST) @ Room 517 AB #154
We study adversarial attacks that manipulate the reward signals to control the actions chosen by a stochastic multi-armed bandit algorithm. We propose the first attack against two popular bandit algorithms: $\epsilon$-greedy and UCB, \emph{without} knowledge of the mean rewards. The attacker is able to spend only logarithmic effort, multiplied by a problem-specific parameter that becomes smaller as the bandit problem gets easier to attack. The result means the attacker can easily hijack the behavior of the bandit algorithm to promote or obstruct certain actions, say, a particular medical treatment. As bandits are seeing increasingly wide use in practice, our study exposes a significant security threat.

Author Information

Kwang-Sung Jun (UW-Madison)
Lihong Li (Google Brain)
Yuzhe Ma (University of Wisconsin-Madison)
Jerry Zhu (University of Wisconsin-Madison)

More from the Same Authors