Effective Hardware-Trojan Feature Extraction Against Adversarial Attacks at Gate-Level Netlists

Kazuki Yamashita*, Tomohiro Kato, Kento Hasegawa, Seira Hidano, Kazuhide Fukushima, Nozomu Togawa

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Recently, with the increase in outsourcing of IC design and manufacturing, the possibility of inserting hardware Trojans, which are circuits with malicious functions, has been pointed out. To prevent this threat, a method to identify hardware Trojans using neural networks has been proposed. On the other hand, adversarial attacks have emerged that modify circuit design information to reduce the accuracy of hardware-Trojan classification by neural networks. Since the features designed by existing methods do not take the attacks into account, it is necessary to consider a new method for countermeasures. In this paper, out of 76 features that are strongly related to hardware-Trojan features, we investigate them from the viewpoint of the robustness against the adversarial attacks on circuit design information and newly propose 24 hardware-Trojan features. We compare the classifiers using the proposed 24 features with the classifiers using 11, 36, 51, and 76 existing features, respectively and confirm that the proposed ones are more robust in identifying hardware Trojans in circuits subjected to the adversarial attacks.

Original languageEnglish
Title of host publicationProceedings - 2022 IEEE 28th International Symposium on On-Line Testing and Robust System Design, IOLTS 2022
EditorsAlessandro Savino, Paolo Rech, Stefano Di Carlo, Dimitris Gizopoulos
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665473552
DOIs
Publication statusPublished - 2022
Event28th IEEE International Symposium on On-Line Testing and Robust System Design, IOLTS 2022 - Torino, Italy
Duration: 2022 Sep 122022 Sep 14

Publication series

NameProceedings - 2022 IEEE 28th International Symposium on On-Line Testing and Robust System Design, IOLTS 2022

Conference

Conference28th IEEE International Symposium on On-Line Testing and Robust System Design, IOLTS 2022
Country/TerritoryItaly
CityTorino
Period22/9/1222/9/14

Keywords

  • adversarial attack
  • gate-level netlist
  • hardware Trojan
  • machine learning
  • neural network

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Information Systems and Management
  • Transportation

Fingerprint

Dive into the research topics of 'Effective Hardware-Trojan Feature Extraction Against Adversarial Attacks at Gate-Level Netlists'. Together they form a unique fingerprint.

Cite this