ExAL: An Exploration Enhanced Adversarial Learning Algorithm

TL;DR

ExAL introduces a novel exploration-enhanced adversarial learning algorithm using EMPSO to generate diverse, impactful perturbations, significantly improving model robustness against adversarial attacks on datasets like MNIST and malware.

Contribution

This paper presents ExAL, a new adversarial learning method that incorporates structured exploration via EMPSO to enhance model defense capabilities.

Findings

ExAL improves robustness on MNIST dataset.

ExAL enhances resilience against malware adversarial attacks.

Experimental results show significant robustness gains.

Abstract

Adversarial learning is critical for enhancing model robustness, aiming to defend against adversarial attacks that jeopardize machine learning systems. Traditional methods often lack efficient mechanisms to explore diverse adversarial perturbations, leading to limited model resilience. Inspired by game-theoretic principles, where adversarial dynamics are analyzed through frameworks like Nash equilibrium, exploration mechanisms in such setups allow for the discovery of diverse strategies, enhancing system robustness. However, existing adversarial learning methods often fail to incorporate structured exploration effectively, reducing their ability to improve model defense comprehensively. To address these challenges, we propose a novel Exploration-enhanced Adversarial Learning Algorithm (ExAL), leveraging the Exponentially Weighted Momentum Particle Swarm Optimizer (EMPSO) to generate optimized adversarial perturbations. ExAL integrates exploration-driven mechanisms to discover perturbations that maximize impact on the model's decision boundary while preserving structural coherence in the data. We evaluate the performance of ExAL on the MNIST Handwritten Digits and Blended Malware datasets. Experimental results demonstrate that ExAL significantly enhances model resilience to adversarial attacks by improving robustness through adversarial learning.