AI for Cybersecurity: Research and Practice - Hardcover

Über die Autorin bzw. den Autor

Houbing Herbert Song is Professor at the Department of Information Systems, University of Maryland, Baltimore County (UMBC).

Elisa Bertino is Samuel D. Conte Distinguished Professor at the Department of Computer Science, Purdue University.

Alvaro Velasquez is a program manager in the Innovation Information Office (I2O) of the Defense Advanced Research Projects Agency (DARPA) and an assistant professor at the University of Colorado Boulder.

Huihui Helen Wang is a teaching professor and director of computing programs in the Khoury College of Computer Sciences at Northeastern University, based in Arlington.

Yan Shoshitaishvili is an Associate Professor at Arizona State University.

Sumit Kumar Jha is Eminent Scholar Chaired Professor of Computer Science at Florida International University (FIU).

Von der hinteren Coverseite

Informative reference on the state of the art in cybersecurity and how to achieve a more secure cyberspace

AI for Cybersecurity presents the state of the art and practice in AI for cybersecurity with a focus on four interrelated defensive capabilities of deter, protect, detect, and respond. The book examines the fundamentals of AI for cybersecurity as a multidisciplinary subject, describes how to design, build, and operate AI technologies and strategies to achieve a more secure cyberspace, and provides why-what-how of each AI technique-cybersecurity task pair to enable researchers and practitioners to make contributions to the field of AI for cybersecurity.

This book is aligned with the National Science and Technology Council’s (NSTC) 2023 Federal Cybersecurity Research and Development Strategic Plan (RDSP) and President Biden’s Executive Order on the Safe, Secure, and Trustworthy Development and Use of Artificial Intelligence. Learning objectives and 200 illustrations are included throughout the text.

Written by a team of highly qualified experts in the field, AI for Cybersecurity discusses topics including:

• Robustness and risks of the methods covered, including adversarial ML threats in model training, deployment, and reuse
• Privacy risks including model inversion, membership inference, attribute inference, re-identification, and deanonymization
• Forensic and formal methods for analyzing, auditing, and verifying security- and privacy-related aspects of AI components
• Use of generative AI systems for improving security and the risks of generative AI systems to security
• Transparency and interpretability/explainability of models and algorithms and associated issues of fairness and bias

AI for Cybersecurity is an excellent reference for practitioners in AI for cybersecurity related industries such as commerce, education, energy, financial services, healthcare, manufacturing, and defense. Fourth year undergraduates and postgraduates in computer science and related programs of study will also find it valuable.