A Survey on Hardware Vulnerability Analysis Using Machine Learning

Abstract

Electronic systems rely on efficient hardware, popularly known as system-on-chip (SoC), to support its core functionalities. A typical SoC consists of diverse components gathered from third-party vendors to reduce SoC design cost and meet time-to-market constraints. Unfortunately, the participation of third-party companies in global supply chain introduces potential security vulnerabilities. There is a critical need to efficiently detect and mitigate hardware vulnerabilities. Machine learning has been successfully used in hardware security verification as well as development of effective countermeasures. There are recent surveys on hardware Trojan detection using machine learning. To the best of our knowledge, there are no comprehensive surveys on utilization of machine learning techniques for detection and mitigation of a wide variety of hardware vulnerabilities including malicious implants (e.g., hardware Trojans), sidechannel leakage, reverse engineering, and supply-chain vulnerabilities (e.g., counterfeiting, overbuilding and recycling). In this paper, we provide a comprehensive survey of hardware vulnerability analysis using machine learning techniques. Specifically, we discuss how existing approaches effectively utilize machine learning algorithms for hardware security verification using simulation-based validation, formal verification as well as side-channel analysis.

A Framework for Automated Exploration of Trojan Attack Space in FPGA Netlists

“…The authors in [12] use bitstream reverse engineering in combination with an unsupervised machine learning (ML) technique [13] for Trojan detection in FPGAs. ML-based techniques have been investigated for Trojan detection as described in [14], [15]. Specifically, works [16], [17] show success in using ML to detect Trojans mapped to FPGAs.…”

“…A LUT is selected if its topological rank is greater than the maximum rank of the Trojan trigger nets. However, we do not need to consider the entire set of Trojan trigger nets, just the number of triggers that can be inserted in the current LUT (lines [12][13][14][15]. If the number of trigger inputs is greater than the LUT inputs, then the (m − i − 1) triggers are selected to be input to the LUT where m is the maximum LUT input, and i is the current number of LUT inputs (lines [16][17][18][19].…”

Enhancing Smart-Contract Security through Machine Learning: A Survey of Approaches and Techniques

“…Unlike other reviews, this article delved into the practical application and effectiveness of various machine-learning techniques in software vulnerability detection and proposed a classification framework to illustrate the types of technologies employed by each method. Pan et al [27] carried out a literature review on hardware vulnerability analysis using machine learning. This review mainly investigated the application and results of machine-learning methods in the field of hardware vulnerability analysis.…”

Energy Meter Patch Resistance and Welding Spot Anomaly Detection Method Based on Machine Vision

“…The authors of [11] designed a smart electric energy meter printed circuit panel consistency detection system based on deep learning technology, which replaced the manual detection mode and was applied in laboratory testing work. The authors of [12] adopted the method of deep learning to detect PCB patch elements, but it had strict requirements on sample data and computing power. The required computing power cost was high, and operation power consumption was large, which could not be popularized in the on-site environment.…”