Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning

TL;DR

This paper reviews the evolution of adversarial machine learning over ten years, highlighting key developments, common misconceptions, and future challenges in securing machine learning models against adversarial attacks.

Contribution

It provides a comprehensive overview of adversarial machine learning history, connecting early non-deep learning work to recent deep learning security research, and discusses limitations and future directions.

Findings

Identifies common misconceptions in security evaluations.

Highlights connections between different research lines.

Discusses limitations and future challenges in secure learning algorithms.

Abstract

Learning-based pattern classifiers, including deep networks, have shown impressive performance in several application domains, ranging from computer vision to cybersecurity. However, it has also been shown that adversarial input perturbations carefully crafted either at training or at test time can easily subvert their predictions. The vulnerability of machine learning to such wild patterns (also referred to as adversarial examples), along with the design of suitable countermeasures, have been investigated in the research field of adversarial machine learning. In this work, we provide a thorough overview of the evolution of this research area over the last ten years and beyond, starting from pioneering, earlier work on the security of non-deep learning algorithms up to more recent work aimed to understand the security properties of deep learning algorithms, in the context of computer vision and cybersecurity tasks. We report interesting connections between these apparently-different lines of work, highlighting common misconceptions related to the security evaluation of machine-learning algorithms. We review the main threat models and attacks defined to this end, and discuss the main limitations of current work, along with the corresponding future challenges towards the design of more secure learning algorithms.