Saving Stochastic Bandits from Poisoning Attacks via Limited Data Verification

Authors: Anshuka Rangi, Long Tran-Thanh, Haifeng Xu, Massimo Franceschetti8054-8061

AAAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical This paper studies bandit algorithms under data poisoning attacks in a bounded reward setting. We show that any bandit algorithm with regret O(log T) can be forced to suffer a regret Ω(T) with an expected amount of contamination O(log T). This amount of contamination is also necessary, as we prove that there exists an O(log T) regret bandit algorithm, specifically the classical Upper Confidence Bound (UCB), that requires Ω(log T) amount of contamination to suffer regret Ω(T).
Researcher Affiliation Academia 1 University of California San Diego 2 University of Warwick, UK 3 University of Virginia, USA
Pseudocode Yes Algorithm 1: Secure-BARBAR
Open Source Code No The paper does not provide any explicit statement or link regarding the availability of open-source code for the described methodology.
Open Datasets No The paper is theoretical and does not involve the use of datasets for training or evaluation. Therefore, no information about publicly available datasets is provided.
Dataset Splits No The paper is theoretical and does not involve dataset splits for training, validation, or testing.
Hardware Specification No The paper does not provide any specific hardware details used for running experiments.
Software Dependencies No The paper does not provide specific software dependencies or version numbers needed to replicate any experiments or algorithmic implementations.
Experiment Setup No The paper is theoretical and does not include details on experimental setup, hyperparameter values, or system-level training settings.