Robust Hardware Trojan Detection Method by Unsupervised Learning of Electromagnetic Signals

Abstract

This article explores the threat posed by Hardware Trojans (HTs), malicious circuits clandestinely embedded in hardware akin to software backdoors. Activation by attackers renders these Trojans capable of inducing malfunctions or leaking confidential information by manipulating the hardware’s normal operation. Despite robust software security, detecting and ensuring normal hardware operation becomes challenging in the presence of malicious circuits. This issue is particularly acute in weapon systems, where HTs can present a significant threat, potentially leading to immediate disablement in adversary countries. Given the severe risks associated with HTs, detection becomes imperative. The study focuses on demonstrating the efficacy of deep learning-based HT detection by comparing and analyzing methods using deep learning with existing approaches. This article proposes utilizing the deep support vector data description (Deep SVDD) model for HT detection. The proposed method outperforms existing methods when detecting untrained HTs. It achieves 92.87% of accuracy on average, which is higher than that of an existing method, 50.00%. This finding contributes valuable insights to the field of hardware security and lays the foundation for practical applications of Deep SVDD in real-world scenarios.