This book explores machine learning (ML) defenses against the many cyberattacks that make our workplaces, schools, private residences, and critical infrastructures vulnerable as a consequence of the dramatic increase in botnets, data ransom, system and network denials of service, sabotage, and data theft attacks. The use of ML techniques for security tasks has been steadily increasing in research and also in practice over the last 10 years. Covering efforts to devise more effective defenses, the book explores security solutions that leverage machine learning (ML) techniques that have recently grown in feasibility thanks to significant advances in ML combined with big data collection and analysis capabilities. Since the use of ML entails understanding which techniques can be best used for specific tasks to ensure comprehensive security, the book provides an overview of the current state of the art of ML techniques for security and a detailed taxonomy of security tasks and corresponding ML techniques that can be used for each task. It also covers challenges for the use of ML for security tasks and outlines research directions.
While many recent papers have proposed approaches for specific tasks, such as software security analysis and anomaly detection, these approaches differ in many aspects, such as with respect to the types of features in the model and the dataset used for training the models. In a way that no other available work does, this book provides readers with a comprehensive view of the complex area of ML for security, explains its challenges, and highlights areas for future research. This book is relevant to graduate students in computer science and engineering as well as information systems studies, and will also be useful to researchers and practitioners who work in the area of ML techniques for security tasks.

Provides a detailed taxonomy of security tasks and related ML-based defenses Uses case studies to illuminate instances in which ML-based defenses would have prevented or mitigated these attacks Discusses the main challenges in using ML for security tasks, initial solutions, and open research directions

Autorentext

Xun Yi is a Professor with the School of Computing Technologies, RMIT University, Australia. His research interests include data privacy protection, cloud and IoT security, blockchain, network security, and applied cryptography. He has published over 300 research papers in international journals and conference proceedings. He serves as an Associate Editor for IEEE Transactions on Dependable and Secure Computing, IEEE Transactions on Knowledge and Data Engineering, ACM Computing Surveys, and Information Sciences. Xuechao Yang is a Lecturer at the School of Computing Technologies, RMIT University, Australia. He holds a bachelor’s degree in Information Technology from RMIT (2013) and a bachelor’s degree in Computer Science with Honours (2014). He earned his Ph.D. from RMIT in 2018. His research interests include cryptosystems, privacy preservation, and blockchain technology. Xiaoning Liu (Member, IEEE) is a Lecturer at the School of Computing Technologies, RMIT University, Australia. Her research focuses on secure computation protocols and privacy-preserving machine learning. She earned her Ph.D. in Computer Science from RMIT in 2022. Her work has appeared in IEEE TDSC, IEEE TIFS, ESORICS, and USENIX Security. She received the Best Paper Award at ESORICS 2021. Andrei Kelarev is a Research Fellow at the University of Newcastle, Australia. He is the author of two books and 198 journal articles. He previously served as Associate Professor at the University of Wisconsin and University of Nebraska (USA), and as a Senior Lecturer at the University of Tasmania. He was Chief Investigator for a major Discovery Grant from the Australian Research Council. His research involves cybersecurity applications of machine learning and data mining. Kwok-Yan Lam (Senior Member, IEEE) received the B.Sc. degree (Hons.) from the University of London in 1987 and the Ph.D. degree from the University of Cambridge in 1990. He is Associate Vice President (Strategy and Partnerships) and Professor at the College of Computing and Data Science, NTU Singapore. He directs the Strategic Centre for Research in Privacy-Preserving Technologies and Systems. Since 2020, he has been a consultant on cyber and technology innovation for INTERPOL. He was previously Professor at Tsinghua University (2002–2010) and faculty at NUS and the University of London. His research areas include distributed systems, IoT security, blockchain protocols, homeland security, and cybersecurity. Mengmeng Yang received her Ph.D. in Computer Science from Deakin University, Australia, in 2019. She is a Research Scientist at Data61, CSIRO, Australia. Previously, she was a Research Fellow at the Strategic Centre for Research in Privacy-Preserving Technologies and Systems (SCRiPTS), NTU Singapore. Her research interests include privacy preservation, data mining, and network security. Xiangning Wang received the B.Sc. degree from Peking University in 2016 and the Ph.D. degree in Computer Science from the University of Hong Kong in 2021. He is a Research Fellow at NTU Singapore. His research interests include privacy-preserving machine learning and differential privacy. Elisa Bertino is a Samuel Conte Distinguished Professor of Computer Science at Purdue University. Her research focuses on data privacy and computer security. She has authored or co-authored over 250 journal articles, 450 conference papers, 9 books, and 35 edited volumes, with more than 300 collaborators. She served as co-editor-in-chief of the GeoInformatica Journal and VLDB Journal and as program chair for ICDE 1998, ECOOP 2000, SACMAT 2002, and EDBT 2004. She is currently Vice President of ACM.

Inhalt
Introduction.- Background on Machine Learning Techniques.- Security Policy earning.- Software Security Analysis.- Hardware Security Analysis.- Detection.- Attack Management.- Case Studies.- Main Challenges in the Use of ML for Security.- Concluding Remarks.