Hardware Trojans classification for gate-level netlists using multi-layer neural networks

Kento Hasegawa; Masao Yanagisawa; Nozomu Togawa

doi:10.1109/IOLTS.2017.8046227

Hardware Trojans classification for gate-level netlists using multi-layer neural networks

Kento Hasegawa, Masao Yanagisawa, Nozomu Togawa

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

36 Citations (Scopus)

Abstract

Recently, due to the increase of outsourcing in IC design and manufacturing, it has been reported that malicious third-party IC vendors often insert hardware Trojans into their products. Especially in IC design step, it is strongly required to detect hardware Trojans because malicious third-party vendors can easily insert hardware Trojans in their products. In this paper, we propose a machine-learning-based hardware-Trojan detection method for gate-level netlists using multi-layer neural networks. First, we extract 11 Trojan-net feature values for each net in a netlist. After that, we classify the nets in an unknown netlist into a set of Trojan nets and that of normal nets using multi-layer neural networks. We obtained at most 100% true positive rate with our proposed method.

Original language	English
Title of host publication	2017 IEEE 23rd International Symposium on On-Line Testing and Robust System Design, IOLTS 2017
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	227-232
Number of pages	6
ISBN (Electronic)	9781538603512
DOIs	https://doi.org/10.1109/IOLTS.2017.8046227
Publication status	Published - 2017 Sep 19
Event	23rd IEEE International Symposium on On-Line Testing and Robust System Design, IOLTS 2017 - Thessaloniki, Greece Duration: 2017 Jul 3 → 2017 Jul 5

Other

Other	23rd IEEE International Symposium on On-Line Testing and Robust System Design, IOLTS 2017
Country	Greece
City	Thessaloniki
Period	17/7/3 → 17/7/5

Keywords

Gate-level netlist
Hardware Trojan
Machine learning
Multi-layer
Neural network

ASJC Scopus subject areas

Electrical and Electronic Engineering
Safety, Risk, Reliability and Quality
Computer Networks and Communications
Hardware and Architecture
Control and Systems Engineering

Access to Document

10.1109/IOLTS.2017.8046227

Fingerprint Dive into the research topics of 'Hardware Trojans classification for gate-level netlists using multi-layer neural networks'. Together they form a unique fingerprint.

Cite this

Hardware Trojans classification for gate-level netlists using multi-layer neural networks. / Hasegawa, Kento; Yanagisawa, Masao ; Togawa, Nozomu.

2017 IEEE 23rd International Symposium on On-Line Testing and Robust System Design, IOLTS 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 227-232 8046227.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Hasegawa, K, Yanagisawa, M & Togawa, N 2017, Hardware Trojans classification for gate-level netlists using multi-layer neural networks. in 2017 IEEE 23rd International Symposium on On-Line Testing and Robust System Design, IOLTS 2017., 8046227, Institute of Electrical and Electronics Engineers Inc., pp. 227-232, 23rd IEEE International Symposium on On-Line Testing and Robust System Design, IOLTS 2017, Thessaloniki, Greece, 17/7/3. https://doi.org/10.1109/IOLTS.2017.8046227

@inproceedings{0506f10c99e648f494884936e7ce78b9,

title = "Hardware Trojans classification for gate-level netlists using multi-layer neural networks",

abstract = "Recently, due to the increase of outsourcing in IC design and manufacturing, it has been reported that malicious third-party IC vendors often insert hardware Trojans into their products. Especially in IC design step, it is strongly required to detect hardware Trojans because malicious third-party vendors can easily insert hardware Trojans in their products. In this paper, we propose a machine-learning-based hardware-Trojan detection method for gate-level netlists using multi-layer neural networks. First, we extract 11 Trojan-net feature values for each net in a netlist. After that, we classify the nets in an unknown netlist into a set of Trojan nets and that of normal nets using multi-layer neural networks. We obtained at most 100% true positive rate with our proposed method.",

keywords = "Gate-level netlist, Hardware Trojan, Machine learning, Multi-layer, Neural network",

author = "Kento Hasegawa and Masao Yanagisawa and Nozomu Togawa",

year = "2017",

month = sep,

day = "19",

doi = "10.1109/IOLTS.2017.8046227",

language = "English",

pages = "227--232",

booktitle = "2017 IEEE 23rd International Symposium on On-Line Testing and Robust System Design, IOLTS 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "23rd IEEE International Symposium on On-Line Testing and Robust System Design, IOLTS 2017 ; Conference date: 03-07-2017 Through 05-07-2017",

}

TY - GEN

T1 - Hardware Trojans classification for gate-level netlists using multi-layer neural networks

AU - Hasegawa, Kento

AU - Yanagisawa, Masao

AU - Togawa, Nozomu

PY - 2017/9/19

Y1 - 2017/9/19

N2 - Recently, due to the increase of outsourcing in IC design and manufacturing, it has been reported that malicious third-party IC vendors often insert hardware Trojans into their products. Especially in IC design step, it is strongly required to detect hardware Trojans because malicious third-party vendors can easily insert hardware Trojans in their products. In this paper, we propose a machine-learning-based hardware-Trojan detection method for gate-level netlists using multi-layer neural networks. First, we extract 11 Trojan-net feature values for each net in a netlist. After that, we classify the nets in an unknown netlist into a set of Trojan nets and that of normal nets using multi-layer neural networks. We obtained at most 100% true positive rate with our proposed method.

AB - Recently, due to the increase of outsourcing in IC design and manufacturing, it has been reported that malicious third-party IC vendors often insert hardware Trojans into their products. Especially in IC design step, it is strongly required to detect hardware Trojans because malicious third-party vendors can easily insert hardware Trojans in their products. In this paper, we propose a machine-learning-based hardware-Trojan detection method for gate-level netlists using multi-layer neural networks. First, we extract 11 Trojan-net feature values for each net in a netlist. After that, we classify the nets in an unknown netlist into a set of Trojan nets and that of normal nets using multi-layer neural networks. We obtained at most 100% true positive rate with our proposed method.

KW - Gate-level netlist

KW - Hardware Trojan

KW - Machine learning

KW - Multi-layer

KW - Neural network

UR - http://www.scopus.com/inward/record.url?scp=85032723104&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032723104&partnerID=8YFLogxK

U2 - 10.1109/IOLTS.2017.8046227

DO - 10.1109/IOLTS.2017.8046227

M3 - Conference contribution

AN - SCOPUS:85032723104

SP - 227

EP - 232

BT - 2017 IEEE 23rd International Symposium on On-Line Testing and Robust System Design, IOLTS 2017

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 23rd IEEE International Symposium on On-Line Testing and Robust System Design, IOLTS 2017

Y2 - 3 July 2017 through 5 July 2017

ER -