Hardware Trojan vulnerability assessment in digital integrated circuits using learnable classifiers

Abstract- In the current distributed integrated circuits (IC) industry, the possibility of adversarial hardware attacks cannot be ignored. Hardware Trojans (HT) attacks may lead to information leakage or failure in security-critical systems. The wide range of HT types and related insertion strategie...

Full description

Saved in:
Bibliographic Details
Main Authors: Hadi Jahanirad, Mohammad Fathi
Format: Article
Language:English
Published: Amirkabir University of Technology 2024-07-01
Series:AUT Journal of Electrical Engineering
Subjects:
Online Access:https://eej.aut.ac.ir/article_5393_c9d2a57a04d56d193c26f4192be51233.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849434238286299136
author Hadi Jahanirad
Mohammad Fathi
author_facet Hadi Jahanirad
Mohammad Fathi
author_sort Hadi Jahanirad
collection DOAJ
description Abstract- In the current distributed integrated circuits (IC) industry, the possibility of adversarial hardware attacks cannot be ignored. Hardware Trojans (HT) attacks may lead to information leakage or failure in security-critical systems. The wide range of HT types and related insertion strategies makes the HT detection process very complex. Consequently, developing IC design methodologies that are robust against HT insertion would be of great merit. To measure the HT robustness, a vulnerability analysis of the proposed circuits should be performed which involves several interrelated factors (e.g. the layout of white spaces distribution, the unutilized routing resources, the activity of the circuit nodes, the delay values of circuit paths, etc.). In this paper, a novel framework is proposed to classify the IC vulnerability level. First, a comprehensive dataset is generated considering different HTs insertion into the ISCAS 85 and ISCAS 89 benchmark circuits. Then extraction of efficient features from the input image is accomplished by pre-trained deep neural networks. Finally, the vulnerability level (which is defined as low vulnerable, moderately vulnerable, and highly vulnerable) of every circuit is extracted using various trained classifiers (Ensemble, SVM, Naïve Bayes, and KNN).  Simulation results confirm a 25% improvement in classification accuracy in the most successful classifier (97%) compared with the most successful previous study (72%).
format Article
id doaj-art-efb4f9d2b7564b02a4619963dd1ee3c1
institution Kabale University
issn 2588-2910
2588-2929
language English
publishDate 2024-07-01
publisher Amirkabir University of Technology
record_format Article
series AUT Journal of Electrical Engineering
spelling doaj-art-efb4f9d2b7564b02a4619963dd1ee3c12025-08-20T03:26:44ZengAmirkabir University of TechnologyAUT Journal of Electrical Engineering2588-29102588-29292024-07-0156341943810.22060/eej.2024.22910.55725393Hardware Trojan vulnerability assessment in digital integrated circuits using learnable classifiersHadi Jahanirad0Mohammad Fathi1Department of Electronics and Communication Engineering, University of Kurdistan, Sanandaj, Kurdistan, IranDepartment of Electronics and Communication Engineering, University of Kurdistan, Sanandaj, Kurdistan, IranAbstract- In the current distributed integrated circuits (IC) industry, the possibility of adversarial hardware attacks cannot be ignored. Hardware Trojans (HT) attacks may lead to information leakage or failure in security-critical systems. The wide range of HT types and related insertion strategies makes the HT detection process very complex. Consequently, developing IC design methodologies that are robust against HT insertion would be of great merit. To measure the HT robustness, a vulnerability analysis of the proposed circuits should be performed which involves several interrelated factors (e.g. the layout of white spaces distribution, the unutilized routing resources, the activity of the circuit nodes, the delay values of circuit paths, etc.). In this paper, a novel framework is proposed to classify the IC vulnerability level. First, a comprehensive dataset is generated considering different HTs insertion into the ISCAS 85 and ISCAS 89 benchmark circuits. Then extraction of efficient features from the input image is accomplished by pre-trained deep neural networks. Finally, the vulnerability level (which is defined as low vulnerable, moderately vulnerable, and highly vulnerable) of every circuit is extracted using various trained classifiers (Ensemble, SVM, Naïve Bayes, and KNN).  Simulation results confirm a 25% improvement in classification accuracy in the most successful classifier (97%) compared with the most successful previous study (72%).https://eej.aut.ac.ir/article_5393_c9d2a57a04d56d193c26f4192be51233.pdfensemble learninglearnable classifiersdeep neural networksdigital circuitsvulnerability analysishardware trojans
spellingShingle Hadi Jahanirad
Mohammad Fathi
Hardware Trojan vulnerability assessment in digital integrated circuits using learnable classifiers
AUT Journal of Electrical Engineering
ensemble learning
learnable classifiers
deep neural networks
digital circuits
vulnerability analysis
hardware trojans
title Hardware Trojan vulnerability assessment in digital integrated circuits using learnable classifiers
title_full Hardware Trojan vulnerability assessment in digital integrated circuits using learnable classifiers
title_fullStr Hardware Trojan vulnerability assessment in digital integrated circuits using learnable classifiers
title_full_unstemmed Hardware Trojan vulnerability assessment in digital integrated circuits using learnable classifiers
title_short Hardware Trojan vulnerability assessment in digital integrated circuits using learnable classifiers
title_sort hardware trojan vulnerability assessment in digital integrated circuits using learnable classifiers
topic ensemble learning
learnable classifiers
deep neural networks
digital circuits
vulnerability analysis
hardware trojans
url https://eej.aut.ac.ir/article_5393_c9d2a57a04d56d193c26f4192be51233.pdf
work_keys_str_mv AT hadijahanirad hardwaretrojanvulnerabilityassessmentindigitalintegratedcircuitsusinglearnableclassifiers
AT mohammadfathi hardwaretrojanvulnerabilityassessmentindigitalintegratedcircuitsusinglearnableclassifiers