Adversarial Robustness for Machine Learning

Adversarial Robustness for Machine Learning 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.

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.

《機器學習的對抗韌性》摘要了這個主題的最新進展，並介紹了對抗攻擊、防禦和驗證的流行算法。各節涵蓋了對抗攻擊、驗證和防禦，主要聚焦於圖像分類應用，這是對抗韌性社區中的標準基準。其他節則討論了超越圖像分類的對抗性示例，超越測試時間攻擊的其他威脅模型，以及對抗韌性的應用。對於研究人員來說，本書提供了一個全面的文獻回顧，總結了該領域的最新進展，可作為未來研究的參考資料。

此外，本書還可以作為研究生課程《對抗韌性或可信機器學習》的教材。儘管機器學習（ML）算法在許多應用中取得了顯著的性能，但最近的研究表明它們對於對抗干擾的韌性不足。韌性不足對於實際應用中的ML模型，如自駕車、機器人控制和醫療系統，帶來了安全擔憂。