Adversarial Machine Learning for Social Good: Reframing the Adversary as an Ally

TL;DR

This paper reviews the emerging field of Adversarial Machine Learning for Social Good (AdvML4G), highlighting its potential to transform adversarial techniques into tools for developing positive, pro-social AI applications and addressing associated challenges.

Contribution

It provides the first comprehensive review, taxonomy, and discussion of AdvML4G, emphasizing its differences from traditional AdvML and exploring its role in promoting social good.

Findings

AdvML4G repurposes adversarial techniques for social good applications.

The paper identifies key challenges and open issues in AdvML4G.

It highlights the importance of collaboration among regulators, practitioners, and researchers.

Abstract

Deep Neural Networks (DNNs) have been the driving force behind many of the recent advances in machine learning. However, research has shown that DNNs are vulnerable to adversarial examples -- input samples that have been perturbed to force DNN-based models to make errors. As a result, Adversarial Machine Learning (AdvML) has gained a lot of attention, and researchers have investigated these vulnerabilities in various settings and modalities. In addition, DNNs have also been found to incorporate embedded bias and often produce unexplainable predictions, which can result in anti-social AI applications. The emergence of new AI technologies that leverage Large Language Models (LLMs), such as ChatGPT and GPT-4, increases the risk of producing anti-social applications at scale. AdvML for Social Good (AdvML4G) is an emerging field that repurposes the AdvML bug to invent pro-social applications. Regulators, practitioners, and researchers should collaborate to encourage the development of pro-social applications and hinder the development of anti-social ones. In this work, we provide the first comprehensive review of the emerging field of AdvML4G. This paper encompasses a taxonomy that highlights the emergence of AdvML4G, a discussion of the differences and similarities between AdvML4G and AdvML, a taxonomy covering social good-related concepts and aspects, an exploration of the motivations behind the emergence of AdvML4G at the intersection of ML4G and AdvML, and an extensive summary of the works that utilize AdvML4G as an auxiliary tool for innovating pro-social applications. Finally, we elaborate upon various challenges and open research issues that require significant attention from the research community.