Adversarial Learning: A Critical Review and Active Learning Study

TL;DR

This paper critically reviews adversarial learning, highlighting limitations, and conducts an experimental study on adversarial active learning, focusing on a mixed sample selection strategy to improve classifier robustness against adversarial attacks.

Contribution

It provides a comprehensive critique of existing adversarial learning methods and introduces an experimental analysis of active learning strategies against adversarial disruptions.

Findings

Identifies key limitations in prior adversarial learning approaches.

Evaluates the effectiveness of mixed sample selection in adversarial active learning.

Shows improved classifier robustness with the proposed strategy.

Abstract

This papers consists of two parts. The first is a critical review of prior art on adversarial learning, identifying some significant limitations of previous works. The second part is an experimental study considering adversarial active learning and an investigation of the efficacy of a mixed sample selection strategy for combating an adversary who attempts to disrupt the classifier learning.