paper-with-me

Papers

Sample Complexity of an Adversarial Attack on UCB-based Best-arm Identification Policy

2022-09-13 · Varsha Pendyala

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.

📄 PDF Abstract BibTeX arXiv:2209.05692

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Attack

Similar Papers 제목 키워드 기반

Attribution of Gradient Based Adversarial Attacks for Reverse Engineering of Deceptions

2021-03-19 · Michael Goebel, Jason Bunk, Srinjoy Chattopadhyay, Lakshmanan Nataraj 외

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 Learning

Best Arm Identification in Contaminated Stochastic Bandits

2021-12-01 · NeurIPS 2021 12 · Arpan Mukherjee, Ali Tajer, Pin-Yu Chen, Payel Das

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

2021-11-14 · NeurIPS 2021 12 · Arpan Mukherjee, Ali Tajer, Pin-Yu Chen, Payel Das

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

2021-02-09 · Blerta Lindqvist

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

2022-10-30 · Jiadi Yao, Xing Chen, Xiao-Lei Zhang, Wei-Qiang Zhang 외

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