Machine Learning for Embedded System Security

This book covers the state-of-the-art security applications of machine learning techniques, including anti-tamper design, IC Counterfeits detection, hardware Trojan identification, deep-learning-based modeling attacks, and malware analysis in embedded systems.

Format: Hardback
Length: 160 pages
Publication date: 23 April 2022
Publisher: Springer Nature Switzerland AG

This comprehensive book delves into the cutting-edge applications of machine learning techniques in the realm of security. In the first part, it explores emerging solutions for anti-tamper design, IC counterfeits detection, and hardware Trojan identification. It also provides an in-depth explanation of the latest developments in deep-learning-based modeling attacks on physically unclonable functions (PUFs), highlighting the design principles of more resilient PUF architectures.

The second part focuses on the use of machine learning to mitigate the risks of security attacks on cyber-physical systems, with a particular emphasis on power plants. It discusses the challenges posed by these systems and the strategies employed to enhance their security.

The third part delves into the principles of malware analysis in embedded systems and highlights the effectiveness of supervised learning techniques in identifying software vulnerabilities. It provides a detailed overview of the techniques and tools used in this field and demonstrates how they can be applied to improve the security of embedded systems.

Overall, this book offers a valuable resource for researchers, practitioners, and students interested in the latest advancements in machine learning and security. It provides a comprehensive understanding of the applications and challenges of these techniques and provides insights into the future of security in the digital age.
This comprehensive book delves into the cutting-edge applications of machine learning techniques in the realm of security. In the first part, it explores emerging solutions for anti-tamper design, IC counterfeits detection, and hardware Trojan identification. It also provides an in-depth explanation of the latest developments in deep-learning-based modeling attacks on physically unclonable functions (PUFs), highlighting the design principles of more resilient PUF architectures.

The second part focuses on the use of machine learning to mitigate the risks of security attacks on cyber-physical systems, with a particular emphasis on power plants. It discusses the challenges posed by these systems and the strategies employed to enhance their security.

The third part delves into the principles of malware analysis in embedded systems and highlights the effectiveness of supervised learning techniques in identifying software vulnerabilities. It provides a detailed overview of the techniques and tools used in this field and demonstrates how they can be applied to improve the security of embedded systems.

Overall, this book offers a valuable resource for researchers, practitioners, and students interested in the latest advancements in machine learning and security. It provides a comprehensive understanding of the applications and challenges of these techniques and provides insights into the future of security in the digital age.

Weight: 436g
Dimension: 235 x 155 (mm)
ISBN-13: 9783030941772
Edition number: 1st ed. 2022