Hardware Trojan Detection Using Thermal Imaging in FPGAs with Combined Features

Abstract

A Hardware Trojan (HT) is a malicious modification of the circuitry of an integrated circuit. The importance of Hardware Trojan detection increases with increase in the complexity of integrated circuits. The possible effects of the insertion of a Hardware Trojan involve a range of harms from leakage of sensitive information to the complete destruction of the integrated circuit itself. Non-invasive methods of Hardware Trojan detection are divided into two general categories: performance testing and side channel analysis. Hardware Trojan detection using thermal imagery is one of the side channel analysis methods which have recently been considered. In this paper, we propose a Hardware Trojan detection method on FPGA, based on thermal image processing of defected and authentic chips assuming that a golden chip is available. We also provide a dataset of thermal images captured from multiple experiments on a certain FPGA board. Each experiment contains 12 images taken in 55 seconds of working FPGA. The Hardware Trojan detection method relies on extracting two different features from images and detecting the presence of a Hardware Trojan using machine learning techniques. Results shows that if proposed method is combined with a basic method, hardware Trojan detection accuracy can be increased, significantly.