Adversarial Machine Learning

Ziv Katzir, Yuval Elovici

Machine Learning for Data Science Handbook: Data Mining and Knowledge …, 2023

This chapter follows the evolution of adversarial machine learning research in recent years, through the lens of the literature. We start by reviewing early work on attack and defense methods and move on to studies that show how adversarial attacks can be applied in the real world. We then list the major outstanding research questions and conclude with research that addresses the domain’s key open question: What is it that makes adversarial examples so difficult to defend against? Our goal is to provide readers with the foundation needed to advance research in this fascinating domain.