Adversarial Robustness for Machine Learning

Pin-Yu Chen, Cho-Jui Hsieh

• Publisher: Academic Press
• Year: 2022
• Print ISBN:
  9780128240205
• eBook ISBN:
  9780128242575
• Topic: Computer Science
• Subtopic: Artificial Intelligence (AI) & Semantics
• Index: Computer Science

Adversarial Robustness for Machine Learning summarizes the recent progress on this topic and introduces popular algorithms on adversarial attack, defense and verification. Sections cover adversarial attack, verification and defense, mainly focusing on image classification applications which are the standard benchmark considered in the adversarial robustness community. Other sections discuss adversarial examples beyond image classification, other threat models beyond testing time attack, and applications on adversarial robustness. For researchers, this book provides a thorough literature review that summarizes latest progress in the area, which can be a good reference for conducting future research. In addition, the book can also be used as a textbook for graduate courses on adversarial robustness or trustworthy machine learning. While machine learning (ML) algorithms have achieved remarkable performance in many applications, recent studies have demonstrated their lack of robustness against adversarial disturbance. The lack of robustness brings security concerns in ML models for real applications such as self-driving cars, robotics controls and healthcare systems. - Summarizes the whole field of adversarial robustness for Machine learning models - Provides a clearly explained, self-contained reference - Introduces formulations, algorithms and intuitions - Includes applications based on adversarial robustness

Table of contents

• Adversarial Robustness for Machine Learning
• Chapter 1 Background and motivation
• Chapter 2 White-box adversarial attacks
• Chapter 3 Black-box adversarial attacks
• Chapter 4 Physical adversarial attacks
• Chapter 5 Training-time adversarial attacks
• Chapter 6 Adversarial attacks beyond image classification
• Chapter 7 Overview of neural network verification
• Chapter 8 Incomplete neural network verification
• Chapter 9 Complete neural network verification
• Chapter 10 Verification against semantic perturbations
• Chapter 11 Overview of adversarial defense
• Chapter 12 Adversarial training
• Chapter 13 Randomization-based defense
• Chapter 14 Certified robustness training
• Chapter 15 Adversary detection
• Chapter 16 Adversarial robustness of beyond neural network models
• Chapter 17 Adversarial robustness in meta-learning and contrastive learning
• Chapter 18 Model reprogramming
• Chapter 19 Contrastive explanations
• Chapter 20 Model watermarking and fingerprinting
• Chapter 21 Data augmentation for unsupervised machine learning
• References
• Index