Adversarial Robustness for 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. Adversarial robustness has become one of the mainstream topics in machine learning with much research carried out, while many companies have started to incorporate security and robustness into their systems. Adversarial Robustness for Machine Learning Models summarizes the recent progress on this topic and introduces popular algorithms on adversarial attack, defense, and veri?cation. It contains 6 parts: The ?rst three parts cover adversarial attack, veri?cation, and defense, mainly focusing on image classi?cation applications, which is the standard benchmark considered in the adversarial robustness community. It then discusses 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 this area, which can be a good reference for conducting future research. It could also be used as a textbook for graduate courses on adversarial robustness or trustworthy machine learning. Summarizes the whole field of adversarial robustness for Machine learning models A clearly explained, self-contained reference Introduces formulations, algorithms and intuitions Includes applications based on adversarial robustness