Today, Artificial Intelligence (AI) and Machine Learning/ Deep Learning (ML/DL) have become the hottest areas in information technology. In our society, many intelligent devices rely on AI/ML/DL algorithms/tools for smart operations. Although AI/ML/DL algorithms and tools have been used in many internet applications and electronic devices, they are also vulnerable to various attacks and threats. 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, among many other attacks and threats. Such attacks can make AI products dangerous to use.
While this discussion focuses on security issues in AI/ML/DL-based systems (i.e., securing the intelligent systems themselves), AI/ML/DL models and algorithms can actually also be used for cyber security (i.e., the use of AI to achieve security).
Since AI/ML/DL security is a newly emergent field, many researchers and industry professionals cannot yet obtain a detailed, comprehensive understanding of this area. This book aims to provide a complete picture of the challenges and solutions to related security issues in various applications. It explains how different attacks can occur in advanced AI tools and the challenges of overcoming those attacks. Then, the book describes many sets of promising solutions to achieve AI security and privacy. The features of this book have seven 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 "using AI to achieve security"
- It covers all the advanced AI attacks and threats with detailed attack models
- It provides multiple solution spaces to the security and privacy issues in AI tools
- The differences among ML and DL security and privacy issues are explained
- Many practical security applications are covered
Preface
About the Editors
Contributors
Part I. Secure AI/ML Systems: Attack Models
1. Machine Learning Attack Models
Jing Lin, Long Dang, Mohamed Rahouti, and Kaiqi Xiong
2. 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
3. Threat of Adversarial Attacks to Deep Learning: A Survey
Linsheng He and Fei Hu
4. Attack Models for Collaborative Deep Learning
Jiamiao Zhao, Fei Hu, and Xiali Hei
5. Attacks on Deep Reinforcement Learning Systems: A Tutorial
Joseph Layton and Fei Hu
6. Trust and Security of Deep Reinforcement Learning
Yen- Hung Chen, Mu- Tien Huang, and Yuh- Jong Hu
7. IoT Threat Modeling using Bayesian Networks
Diego Heredia
Part II. Secure AI/ML Systems: Defenses
8. Survey of Machine Learning Defense Strategies
Joseph Layton, Fei Hu, and Xiali Hei
9. Defenses Against Deep Learning Attacks
Linsheng He and Fei Hu
10. Defensive Schemes for Cyber Security of Deep Reinforcement Learning
Jiamiao Zhao, Fei Hu, and Xiali Hei
11. Adversarial Attacks on Machine Learning Models in Cyber-Physical Systems
Mahbub Rahman and Fei Hu
12. Federated Learning and Blockchain: An Opportunity for Artificial Intelligence with Data Regulation
Darine Ameyed, Fehmi Jaafar, Riadh ben Chaabene, and Mohamed Cheriet
Part III. Using AI/ML Algorithms for Cyber Security
13. Using Machine Learning for Cyber Security: Overview
D. Roshni Thanka, G. Jaspher W. Kathrine, and E. Bijolin Edwin
14. Performance of Machine Learning and Big Data Analytics Paradigms in Cyber Security
Gabriel Kabanda
15. Using ML and DL Algorithms for Intrusion Detection in Industrial Internet of Things.
Nicole do Vale Dalarmelina, Pallavi Arora, Baljeet Kaur, Rodolfo Ipolito Meneguette, and Marcio Andrey Teixeira
Part IV. Applications
16. On Detecting Interest Flooding Attacks in Named Data Networking (NDN)-based IoT Searches
Hengshuo Liang, Lauren Burgess, Weixian Liao, Qianlong Wang, and Wei Yu
17. Attack on Fraud Detection Systems in Online Banking Using Generative Adversarial Networks
Jerzy Surma and Krzysztof Jagiełło
18. An Artificial Intelligence-assisted Security Analysis of Smart Healthcare Systems
Nur Imtiazul Haque and Mohammad Ashiqur Rahman
19. A User-centric Focus for Detecting Phishing Emails
Regina Eckhardt and Sikha Bagui
Biography
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.
