Golden chip-Free Hardware Trojan Detection through Side-Channel Analysis using Machine Learning

Design and fabrication outsourcing has made integrated circuits vulnerable to malicious modifications by third parties known as hardware Trojan (HT). Over the last decade, the use of side-channel measurements for detecting the malicious manipulation of the chip has been extensively studied. However, the suggested approaches mostly suffer from two major limitations: reliance on trusted identical chip (e.i. golden chip); untraceable footprints of subtle hardware Trojans, which remain inactive during the testing phase. To overcome these shortcomings, we propose a novel idea of maintaining a dynamic model of the integrated circuit throughout its life cycle to detect HT that might have been injected anywhere in the supply chain. In this thesis, we thoroughly investigate post-silicon HT detection through side-channel analysis using various machine learning models. In this regard, we gather a comprehensive dataset of power and Electromagnetic (EM) side-channel signals for hardware Trojan benchmarks from Trust Hub \cite{tehranipoor2016trusthub} benchmarks to develop a statistical model of the chip for HT detection. We release our collected power and EM side-channel signals for various HT benchmarks as a public dataset in \cite{dataset}. Afterward, we explore many machine learning models and various techniques that eventually lead to three approaches for golden chip-free HT detection and HT detection models that outperform the existing methods. Our two recently published papers \cite{HTM,HTnet} are also developed based on this dataset, and they provide further ideas on how to use the dataset to construct an HT detection model