Deep Learning for Computational Problems in Hardware Security: Modeling Attacks on Strong Physically Unclonable Function Circuits

The book provides a comprehensive overview of traditional and advanced machine learning methods for hardware security applications, focusing on launching potent modeling attacks on Physically Unclonable Function (PUF) circuits. It is self-contained and includes reference software code and datasets for replication.

Format: Hardback
Length: 84 pages
Publication date: 16 September 2022
Publisher: Springer Verlag, Singapore

This comprehensive book delves into the realm of traditional machine learning methods and cutting-edge deep learning practices, with a specific focus on their application in hardware security. It explores the techniques of launching powerful modeling attacks on Physically Unclonable Function (PUF) circuits, which are emerging as promising hardware security primitives. The book is self-contained and provides a thorough background on PUF circuits, along with the necessary mathematical foundation for traditional and advanced machine learning techniques, including support vector machines, logistic regression, neural networks, and deep learning. It serves as a valuable resource for researchers and practitioners in the field of hardware security, as well as for graduate-level courses on hardware security and the application of machine learning in this domain.

One of the remarkable aspects of this book is its availability of comprehensive reference software code and datasets. These resources enable readers to replicate the experiments described in the book and further explore the topics covered. This hands-on approach enhances the learning experience and allows readers to apply the knowledge gained to real-world scenarios.

The book is organized into well-structured chapters, each dedicated to a specific aspect of hardware security and machine learning. The introduction provides an overview of the topics covered, while subsequent chapters delve into the theoretical foundations, implementation details, and practical applications of the discussed techniques. The authors have done an excellent job of explaining complex concepts in a clear and concise manner, making the book accessible to a wide range of readers, including those with limited technical background.

In conclusion, this book is a must-read for anyone interested in hardware security and machine learning. It offers a comprehensive and up-to-date overview of traditional and advanced machine learning techniques, with a particular emphasis on their application in hardware security. The availability of reference software code and datasets further enhances its value as a self-learning resource and enables readers to apply the knowledge gained to real-world scenarios. I highly recommend this book to researchers, practitioners, and students in the field of hardware security.

Weight: 325g
Dimension: 235 x 155 (mm)
ISBN-13: 9789811940163
Edition number: 1st ed. 2023