Robust Active Learning (RoAL): Countering Dynamic Adversaries in Active Learning with Elastic Weight Consolidation

TL;DR

This paper presents elsarticle.cls, a LaTeX document class engineered for consistent, publication-ready formatting of articles for Elsevier journals. It emphasizes compatibility with standard LaTeX packages, reduces packaging conflicts, and offers configurable layouts (preprint, final styles, and column settings). The work details the key design differences from the older elsart.cls, installation procedures from common repositories, and guidelines for frontmatter, figures, and tables. The result is a robust, interoperable tool that simplifies preparing submissions that conform to Elsevier's formatting requirements.

Abstract

Despite significant advancements in active learning and adversarial attacks, the intersection of these two fields remains underexplored, particularly in developing robust active learning frameworks against dynamic adversarial threats. The challenge of developing robust active learning frameworks under dynamic adversarial attacks is critical, as these attacks can lead to catastrophic forgetting within the active learning cycle. This paper introduces Robust Active Learning (RoAL), a novel approach designed to address this issue by integrating Elastic Weight Consolidation (EWC) into the active learning process. Our contributions are threefold: First, we propose a new dynamic adversarial attack that poses significant threats to active learning frameworks. Second, we introduce a novel method that combines EWC with active learning to mitigate catastrophic forgetting caused by dynamic adversarial attacks. Finally, we conduct extensive experimental evaluations to demonstrate the efficacy of our approach. The results show that RoAL not only effectively counters dynamic adversarial threats but also significantly reduces the impact of catastrophic forgetting, thereby enhancing the robustness and performance of active learning systems in adversarial environments.