Applications of Machine Learning in Hardware Security and Trust

Yiorgos Makris  - The University of Texas at Dallas, USA


Over the last fifteen years, hardware security and trust has evolved into a major new area of research at the intersection of semiconductor manufacturing, VLSI design and test, computer-aided design, architecture and system security. During the same period, machine learning has experienced a major revival in interest and has flourished from a nearly forgotten area to the talk of the town. In this lecture, we will first review various machine learning-based solutions which have been developed to address a number of concerns in hardware security and trust, including hardware Trojan detection, counterfeit IC identification, provenance attestation, hardware-based malware detection, side-channel attacks, PUF modeling, design obfuscation/de-obfuscation, etc. Then, we will examine the key attributes of these problems which make them amenable to machine learning-based solutions and we will discuss the potential and the fundamental limitations of such approaches. Lastly, we will ponder the role of and necessity for advanced contemporary machine learning methods in the context of hardware security and we will conclude with suggestions for avoiding common pitfalls when employing such methods.


The course will cover basic theory and technology for integrated optics, with focus on Silicon-based integrated optics. While integrated optics is a vast field, we will cover a selected list of topics that are needed for an understanding of opto-electronic systems with particular applications in computing and communication systems. As it is desirable to integrate optical devices on a larger scale, we will focus mostly on linear optical technologies that are amenable to such an integration with electronic systems in conventional silicon manufacturing processes. The tutorial is targeted toward electrical and computer engineers and computer scientists, and should be accessible to graduate students in these areas. Tentative topics are:

  • Introductions
  • Hardware Security and Trust
  • Applications of Machine Learning
    • Hardware Trojan Detection
    • Counterfeit IC Identification
    • Provenance Attestation
    • Hardware-Based Malware Detection
    • Workload Execution Forensics
    • Side Channel Attacks
    • PUF Modeling
    • Design Obfuscation / De-Obfuscation
    • …    
  • Metrics
  • Why/When is Machine Learning the Right Approach? 
  • Deep vs. Shallow Machine Learning
  • Fallacies and Pitfalls
  • Conclusions