Cover Image

Net Classification Based on Testability and Netlist Structural Features for Hardware Trojan Detection

As integrated chip (IC) is one of the most essential components for communication devices, enhancing the integrity of hardware security is essential to prevent any security breach. Implantation of Hardware Trojan (HT) into the IC is one of the most threatening hardware security risks since most of t...

Full description

Saved in:
Bibliographic Details
Main Authors: Kok, C.H., Ooi, C.Y., Inoue, M., Moghbel, M., Baskara Dass, S., Choo, H.S., Ismail, N., Hussin, F.A.
Format: Conference or Workshop Item
Published: IEEE Computer Society 2019
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85078342247&doi=10.1109%2fATS47505.2019.00020&partnerID=40&md5=30e5630a1ce5cba00110ca1b7808c665
http://eprints.utp.edu.my/23663/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utp.eprints.23663
record_format eprints
spelling my.utp.eprints.236632021-08-19T08:08:19Z Net Classification Based on Testability and Netlist Structural Features for Hardware Trojan Detection Kok, C.H. Ooi, C.Y. Inoue, M. Moghbel, M. Baskara Dass, S. Choo, H.S. Ismail, N. Hussin, F.A. As integrated chip (IC) is one of the most essential components for communication devices, enhancing the integrity of hardware security is essential to prevent any security breach. Implantation of Hardware Trojan (HT) into the IC is one of the most threatening hardware security risks since most of the IC design and fabrication phases are outsourced to third-party foundries. Gate-level netlist inspection is utterly important as HT could be easily hidden among the primitives of the circuit which makes the detection challenging. Previously, HT detection methods for gate-level netlist were mainly based on either net testability or net's structural features. In this paper, we proposed to consolidate these two types of features into a single feature vector to train supervised machine learning classifiers. We also analyzed the performance of the classifiers based on different combinations of features using Minimum Redundancy and Maximum Relevance (mRMR) technique. Using the best feature combination, we achieved a 99.85 True Positive Rate (TPR), 99.95 True Negative Rate (TNR) and 99.90 accuracy (ACC). The results were validated using 10-fold cross-validation. © 2019 IEEE. IEEE Computer Society 2019 Conference or Workshop Item NonPeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85078342247&doi=10.1109%2fATS47505.2019.00020&partnerID=40&md5=30e5630a1ce5cba00110ca1b7808c665 Kok, C.H. and Ooi, C.Y. and Inoue, M. and Moghbel, M. and Baskara Dass, S. and Choo, H.S. and Ismail, N. and Hussin, F.A. (2019) Net Classification Based on Testability and Netlist Structural Features for Hardware Trojan Detection. In: UNSPECIFIED. http://eprints.utp.edu.my/23663/
institution Universiti Teknologi Petronas
building UTP Resource Centre
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Petronas
content_source UTP Institutional Repository
url_provider http://eprints.utp.edu.my/
description As integrated chip (IC) is one of the most essential components for communication devices, enhancing the integrity of hardware security is essential to prevent any security breach. Implantation of Hardware Trojan (HT) into the IC is one of the most threatening hardware security risks since most of the IC design and fabrication phases are outsourced to third-party foundries. Gate-level netlist inspection is utterly important as HT could be easily hidden among the primitives of the circuit which makes the detection challenging. Previously, HT detection methods for gate-level netlist were mainly based on either net testability or net's structural features. In this paper, we proposed to consolidate these two types of features into a single feature vector to train supervised machine learning classifiers. We also analyzed the performance of the classifiers based on different combinations of features using Minimum Redundancy and Maximum Relevance (mRMR) technique. Using the best feature combination, we achieved a 99.85 True Positive Rate (TPR), 99.95 True Negative Rate (TNR) and 99.90 accuracy (ACC). The results were validated using 10-fold cross-validation. © 2019 IEEE.
format Conference or Workshop Item
author Kok, C.H.
Ooi, C.Y.
Inoue, M.
Moghbel, M.
Baskara Dass, S.
Choo, H.S.
Ismail, N.
Hussin, F.A.
spellingShingle Kok, C.H.
Ooi, C.Y.
Inoue, M.
Moghbel, M.
Baskara Dass, S.
Choo, H.S.
Ismail, N.
Hussin, F.A.
Net Classification Based on Testability and Netlist Structural Features for Hardware Trojan Detection
author_facet Kok, C.H.
Ooi, C.Y.
Inoue, M.
Moghbel, M.
Baskara Dass, S.
Choo, H.S.
Ismail, N.
Hussin, F.A.
author_sort Kok, C.H.
title Net Classification Based on Testability and Netlist Structural Features for Hardware Trojan Detection
title_short Net Classification Based on Testability and Netlist Structural Features for Hardware Trojan Detection
title_full Net Classification Based on Testability and Netlist Structural Features for Hardware Trojan Detection
title_fullStr Net Classification Based on Testability and Netlist Structural Features for Hardware Trojan Detection
title_full_unstemmed Net Classification Based on Testability and Netlist Structural Features for Hardware Trojan Detection
title_sort net classification based on testability and netlist structural features for hardware trojan detection
publisher IEEE Computer Society
publishDate 2019
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85078342247&doi=10.1109%2fATS47505.2019.00020&partnerID=40&md5=30e5630a1ce5cba00110ca1b7808c665
http://eprints.utp.edu.my/23663/
_version_ 1738656503951261696
score 13.211869

Similar Items