AI, machine learning and deep learning a security perspective edited by Fei Hu and Xiali Hei.

Includes bibliographical references and index.

Machine learning attack models / Jing Lin, Long Dang, Mohamed Rahouti, Kaiqi Xiong -- Adversarial machine learning : a new threat paradigm for next-generation wireless communications / Yalin E. Sagduyu, Yi Shi, Tugba Erpek, William Headley, Bryse Flowers, George Stantchev, Zhuo Lu, and Brian Jalaian -- Threat of adversarial attacks to deep learning : a survey / Linsheng He, Fei Hu.

"Today Artificial Intelligence (AI) and Machine/Deep Learning (ML/DL) have become the hottest areas in the information technology. In our society, there are so many intelligent devices that rely on AI/ML/DL algorithms/tools for smart operations. Although AI/ML/DL algorithms/tools have used in many Internet applications and electronic devices, they are also vulnerable to various attacks and threats. The AI parameters may be distorted by the internal attacker; the DL input samples may be polluted by adversaries; the ML model may be misled by changing the classification boundary, and many other attacks/threats. Those attacks make the AI products dangerous to use. While the above discussion focuses on the security issues in AI/ML/DL-based systems (i.e., securing the intelligent systems themselves), AI/ML/DL models/algorithms can be used for cyber security (i.e., use AI to achieve security). Since the AI/ML/DL security is a new emergent field, many researchers and industry people cannot obtain detailed, comprehensive understanding of this area. This book aims to provide a complete picture on the challenges and solutions to the security issues in various applications. It explains how different attacks can occur in advanced AI tools and the challenges of overcoming those attacks. Then many sets of promising solutions are described to achieve AI security and privacy in this book. The features of this book consist of 7 aspects: This is the first book to explain various practical attacks and countermeasures to AI systems; Both quantitative math models and practical security implementations are provided; It covers both "securing the AI system itself" and "use AI to achieve security"; It covers all the advanced AI attacks and threats with detailed attack models; It provides the multiple solution spaces to the security and privacy issues in AI tools; The differences among ML and DL security/privacy issues are explained. Many practical security applications are covered"--