Sample Complexity of an Adversarial Attack on UCB-based Best-arm Identification Policy
In this work I study the problem of adversarial perturbations to rewards, in a Multi-armed bandit (MAB) setting. Specifically, I focus on an adversarial attack to a UCB type best-arm identification policy applied to a stochastic MAB. The UCB attack presented in [1] results in pulling a target arm K very often. I used the attack model of [1] to derive the sample complexity required for selecting target arm K as the best arm. I have proved that the stopping condition of UCB based best-arm identification algorithm given in [2], can be achieved by the target arm K in T rounds, where T depends only on the total number of arms and $\sigma$ parameter of $\sigma^2-$ sub-Gaussian random rewards of the arms.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial AttackSimilar Papers 제목 키워드 기반
Attribution of Gradient Based Adversarial Attacks for Reverse Engineering of Deceptions
Machine Learning (ML) algorithms are susceptible to adversarial attacks and deception both during training and deployment. Automatic reverse engineering of the toolchains behind these adversarial machine learning attacks…
AttributeBIG-bench Machine LearningBest Arm Identification in Contaminated Stochastic Bandits
This paper investigates the problem of best arm identification in {\sl contaminated} stochastic multi-arm bandits. In this setting, the rewards obtained from any arm are replaced by samples from an adversarial model with…
Mean-based Best Arm Identification in Stochastic Bandits under Reward Contamination
This paper investigates the problem of best arm identification in $\textit{contaminated}$ stochastic multi-arm bandits. In this setting, the rewards obtained from any arm are replaced by samples from an adversarial model…
Target Training Does Adversarial Training Without Adversarial Samples
Neural network classifiers are vulnerable to misclassification of adversarial samples, for which the current best defense trains classifiers with adversarial samples. However, adversarial samples are not optimal for stee…
Symmetric Saliency-based Adversarial Attack To Speaker Identification
Adversarial attack approaches to speaker identification either need high computational cost or are not very effective, to our knowledge. To address this issue, in this paper, we propose a novel generation-network-based a…
Adversarial AttackDecoderSpeaker Identification