A Hardware Trojan Detection and Diagnosis Method for Gate-Level Netlists Based on Different Machine Learning Algorithms

Abstract

The design complexity and outsourcing trend of modern integrated circuits (ICs) have increased the chance for adversaries to implant hardware Trojans (HTs) in the development process. To effectively defend against this hardware-based security threat, many solutions have been reported in the literature, including dynamic and static techniques. However, there is still a lack of methods that can simultaneously detect and diagnose HT circuits with high accuracy and low time complexity. Therefore, to overcome these limitations, this paper presents an HT detection and diagnosis method for gate-level netlists (GLNs) based on different machine learning (ML) algorithms. Given a GLN, the proposed method first partitions it into several circuit cones and extracts seven HT-related features from each cone. Then, we repeat this process for the sample GLN to construct a dataset for the next step. After that, we use K-Nearest Neighbor (KNN), Decision Tree (DT) and Naive Bayes (NB) to classify all circuit cones of the target GLN. Finally, we determine whether each circuit cone is HT-implanted through the label, completing the HT detection and diagnosis for target GLN. We have applied our method to 11 GLNs from ISCAS’85 and ISCAS’89 benchmark suites. As shown in experimental results of the three ML algorithms used in our method: (1) NB costs shortest time and achieves the highest average true positive rate (ATPR) of 100%; (2) DT costs longest time but achieve the highest average true negative rate (ATNR) of 98.61%; (3) Compared to NB and DT, KNN costs a slightly longer time than NB but the ATPR and ATNR values are approximately close to DT. Moreover, it can also report the possible implantation location of a Trojan instance according to the detecting results.

A Hardware Trojan Detection and Diagnosis Method for Gate-Level Netlists Based on Machine Learning and Graph Theory

“…They partitioned the circuit into multiple cones and extracted the HT feature values of that method, and they then diagnosed the location of the HT circuits. Huang et al [28] presented an HT detection and diagnosis method for GLNs based on different ML models. They classified all the circuit cones of the target GLN using different ML models; they then determined whether each circuit cone was HT-implanted through the label.…”

“…For another comparative experiment, we chose [28], which implemented GLHT detection using ML with different models and achieved good results. Table 12 shows the comparative detection results; it is evident that, although the TNR in this article was lower compared to [28], the F1 score generally tended to be higher than that of [28].…”

“…For another comparative experiment, we chose [28], which implemented GLHT detection using ML with different models and achieved good results. Table 12 shows the comparative detection results; it is evident that, although the TNR in this article was lower compared to [28], the F1 score generally tended to be higher than that of [28]. The results suggest that the model has a good trade-off between correctly identifying positive instances (precision) and capturing all positive instances (recall).…”

Data Augmented Hardware Trojan Detection Using Label Spreading Algorithm Based Transductive Learning for Edge Computing-Assisted IoT Devices

“…It used feature importance function to choose 49 optimal features, but class imbalance problem had not been dealt with. An effort to combine structural features based HTD with circuit partitioning schemes for Trojan localization, was attempted in [41], [42]. An unsupervised HTD approach termed PL-HTD, where principal component analysis generates an optimal feature set for unsupervised classification using a local outlier factor algorithm had been attempted [43].…”

Towards Trust Hardware Deployment of Edge Computing: Mitigation of Hardware Trojans Based on Evolvable Hardware

“…The dynamic detection method is designed to detect HT circuits inserted by untrusted foundries during the manufacturing process [4][5][6][7][8][9]. The static detection methods use testability-based structural features extracted from IC design files to match HTs' features [10][11][12][13][14]. However, since attackers may create special types/hard-to-activate HTs, there is no complete guarantee that HT circuits can be identified during the detection phase.…”