AI, Machine Learning and Deep Learning
A Security Perspective
- Available for pre-order on May 15, 2023. Item will ship after June 5, 2023
Prices & shipping based on shipping country
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.
Table of Contents
Part I. Secure AI/ML Systems: Attack Models
1. Machine Learning Attack Models by Jing Lin, Long Dang, Mohamed Rahouti, Kaiqi Xiong. 2. Adversarial Machine Learning: A New Threat Paradigm for Next-Generation Wireless Communications by Yalin E. Sagduyu, Yi Shi, Tugba Erpek, William Headley, Bryse Flowers, George Stantchev, Zhuo Lu, and Brian Jalaian. 3. Threat of Adversarial Attacks to Deep Learning: A survey by Linsheng He, Fei Hu. 4. Attack Models for Collaborative Deep Learning by Jiamiao Zhao, Fei Hu, Xiali Hei. 5. Attacks on Deep Reinforcement Learning Systems: A Tutorial by Joseph Layton Fei Hu. 6. Trust and Security of Deep Reinforcement Learning by Yen-Hung Chen, Mu-Tien Huang, and Yuh-Jong Hu. 7. IoT threat modeling using Bayesian networks by Diego Heredia.
Part II. Secure AI/ML Systems: Defenses
8. Survey of Machine Learning Defense Strategies by Joseph Layton, Fei Hu, Xiali Hei. 9. Defenses to Deep Learning Attacks by Linsheng He, Fei Hu. 10. Defensive Schemes for Cyber Security of Deep Reinforcement Learning by Jiamiao Zhao, Fei Hu, Xiali Hei. 11. Adversarial Attacks on Machine Learning models in Cyber Physical System by Mahbub Rahman, Fei Hu. 12. Federated learning and Blockchain: An opportunity for Artificial Intelligence with data regulation by Darine Amayed, Fehmi Jaafar, Riadh Ben Chaabene, and Mohamed Cheriet.
Part III. Use AI/ML Algorithms for Cyber Security
13. Use Machine learning for Cyber Security: Overview by Dr. D. Roshni Thanka, Dr. G. Jaspher W. Kathrine, Dr. E. Bijolin Edwin. 14. Performance of Machine Learning and Big Data Analytics paradigms in Cybersecurity by Gabriel Kabanda. 15. Using ML and DL algorithms for Intrusion Detection in Industrial Internet of Things by Nicole do Vale Dalarmelina, Pallavi Arora, Baljeet Kaur, Rodolfo Ipolito Meneguette, Marcio Andrey Teixeira.
Part IV. Applications
16. On Detecting Interest Flooding Attacks in Named Data Networking (NDN) based IoT Search by Hengshuo Liang, Lauren Burgess, Weixian Liao, Qianlong Wang, and Wei Yu. 17. Attack on fraud detection system in online banking using generative adversarial networks by Jerzy Surma, Krzysztof Jagiełło. 18. An Artificial Intelligence-Assisted Security Analysis of Smart Healthcare Systems by Nur Imtiazul Haque and Mohammad Ashiqur Rahman. 19. A User-Centric Focus for Detecting Phishing Emails by Regina Eckhardt and Sikha Bagui.
Dr. Fei Hu is a professor in the department of Electrical and Computer Engineering at the University of Alabama. He has published over 10 technical books with CRC press. His research focus includes cyber security and networking. He obtained his Ph.D. degrees at Tongji University (Shanghai, China) in the field of Signal Processing (in 1999), and at Clarkson University (New York, USA) in Electrical and Computer Engineering (in 2002). He has published over 200 journal/conference papers and books. Dr. Hu's research has been supported by U.S. National Science Foundation, Cisco, Sprint, and other sources. He won the school’s President’s Faculty Research Award (<1% faculty were awarded each year) in 2020.
Dr. Xiali (Sharon) Hei is an assistant professor in the School of Computing and Informatics at the University of Louisiana at Lafayette. Her research focus is cyber and physical security. Prior to joining the University of Louisiana at Lafayette, she was an assistant professor at Delaware State University from 2015-2017 and Frostburg State University 2014-2015. Sharon received his Ph.D. in computer science from Temple University in 2014, focusing on computer security.