Adversarial Robustness for Machine Learning - Humanitas
Cho-Jui Hsieh

Adversarial Robustness for Machine Learning

Balsavo 0
ISBN: 9780128240205
Autorius : Cho-Jui Hsieh
Leidimo metai: 2022
Leidėjas: Academic Press
Leidinio kalba: Anglų
Formatas: Minkšti viršeliai
Formatas: 11.25×8.5
Aprašymas
<p><i>Adversarial Robustness for Machine Learning</i> summarizes the recent progress on this topic and introduces popular algorithms on adversarial attack, defense and veri?cation. Sections cover adversarial attack, veri?cation and defense, mainly focusing on image classi?cation 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. </p> <p>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. </p>

Atsiliepimai (0)
Palikite atsiliepimą