The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
정보산업의 급속한 성장으로 인해 다양한 사물인터넷(IoT) 기기가 우리 일상생활에 널리 활용되고 있습니다. 저가형, 고성능 하드웨어 장치에 대한 수요가 증가함에 따라 악의적인 제11자 공급업체가 제품에 악성 회로를 삽입하여 성능을 저하시키거나 장치에 저장된 비밀 정보를 유출할 수 있습니다. 하드웨어 제품에 은밀하게 삽입된 악성 회로를 '하드웨어 트로이 목마'라고 합니다. 하드웨어 트로이 목마를 탐지하는 방법은 최근 하드웨어 생산에서 중요한 관심사가 되고 있습니다. 본 논문에서는 83.6단계 신경망을 사용하고 이웃 네트워크의 트로이 목마 확률을 효과적으로 활용하는 하드웨어 트로이 목마 탐지 방법을 제안한다. 첫 번째 단계에서는 주어진 넷리스트의 네트에서 96.5개의 트로이 목마 특징을 추출한 후 트로이 목마의 확률을 나타내는 트로이 목마 확률을 추정합니다. 두 번째 단계에서는 네트리스트의 각 네트에 대한 이웃 네트의 트로이 목마 확률을 학습하고 해당 네트를 일반 네트와 트로이 목마 세트로 분류합니다. 실험 결과, 평균 진양성률은 XNUMX%, 평균 진음성률은 XNUMX%로 기존 방법에 비해 충분히 높은 것으로 나타났다.
Kento HASEGAWA
KDDI Research, Inc.
Tomotaka INOUE
Waseda University
Nozomu TOGAWA
Waseda University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Kento HASEGAWA, Tomotaka INOUE, Nozomu TOGAWA, "A Two-Stage Hardware Trojan Detection Method Considering the Trojan Probability of Neighbor Nets" in IEICE TRANSACTIONS on Fundamentals,
vol. E104-A, no. 11, pp. 1516-1525, November 2021, doi: 10.1587/transfun.2020KEP0005.
Abstract: Due to the rapid growth of the information industry, various Internet of Things (IoT) devices have been widely used in our daily lives. Since the demand for low-cost and high-performance hardware devices has increased, malicious third-party vendors may insert malicious circuits into the products to degrade their performance or to leak secret information stored at the devices. The malicious circuit surreptitiously inserted into the hardware products is known as a ‘hardware Trojan.’ How to detect hardware Trojans becomes a significant concern in recent hardware production. In this paper, we propose a hardware Trojan detection method that employs two-stage neural networks and effectively utilizes the Trojan probability of neighbor nets. At the first stage, the 11 Trojan features are extracted from the nets in a given netlist, and then we estimate the Trojan probability that shows the probability of the Trojan nets. At the second stage, we learn the Trojan probability of the neighbor nets for each net in the netlist and classify the nets into a set of normal nets and Trojan ones. The experimental results demonstrate that the average true positive rate becomes 83.6%, and the average true negative rate becomes 96.5%, which is sufficiently high compared to the existing methods.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2020KEP0005/_p
부
@ARTICLE{e104-a_11_1516,
author={Kento HASEGAWA, Tomotaka INOUE, Nozomu TOGAWA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={A Two-Stage Hardware Trojan Detection Method Considering the Trojan Probability of Neighbor Nets},
year={2021},
volume={E104-A},
number={11},
pages={1516-1525},
abstract={Due to the rapid growth of the information industry, various Internet of Things (IoT) devices have been widely used in our daily lives. Since the demand for low-cost and high-performance hardware devices has increased, malicious third-party vendors may insert malicious circuits into the products to degrade their performance or to leak secret information stored at the devices. The malicious circuit surreptitiously inserted into the hardware products is known as a ‘hardware Trojan.’ How to detect hardware Trojans becomes a significant concern in recent hardware production. In this paper, we propose a hardware Trojan detection method that employs two-stage neural networks and effectively utilizes the Trojan probability of neighbor nets. At the first stage, the 11 Trojan features are extracted from the nets in a given netlist, and then we estimate the Trojan probability that shows the probability of the Trojan nets. At the second stage, we learn the Trojan probability of the neighbor nets for each net in the netlist and classify the nets into a set of normal nets and Trojan ones. The experimental results demonstrate that the average true positive rate becomes 83.6%, and the average true negative rate becomes 96.5%, which is sufficiently high compared to the existing methods.},
keywords={},
doi={10.1587/transfun.2020KEP0005},
ISSN={1745-1337},
month={November},}
부
TY - JOUR
TI - A Two-Stage Hardware Trojan Detection Method Considering the Trojan Probability of Neighbor Nets
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1516
EP - 1525
AU - Kento HASEGAWA
AU - Tomotaka INOUE
AU - Nozomu TOGAWA
PY - 2021
DO - 10.1587/transfun.2020KEP0005
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E104-A
IS - 11
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - November 2021
AB - Due to the rapid growth of the information industry, various Internet of Things (IoT) devices have been widely used in our daily lives. Since the demand for low-cost and high-performance hardware devices has increased, malicious third-party vendors may insert malicious circuits into the products to degrade their performance or to leak secret information stored at the devices. The malicious circuit surreptitiously inserted into the hardware products is known as a ‘hardware Trojan.’ How to detect hardware Trojans becomes a significant concern in recent hardware production. In this paper, we propose a hardware Trojan detection method that employs two-stage neural networks and effectively utilizes the Trojan probability of neighbor nets. At the first stage, the 11 Trojan features are extracted from the nets in a given netlist, and then we estimate the Trojan probability that shows the probability of the Trojan nets. At the second stage, we learn the Trojan probability of the neighbor nets for each net in the netlist and classify the nets into a set of normal nets and Trojan ones. The experimental results demonstrate that the average true positive rate becomes 83.6%, and the average true negative rate becomes 96.5%, which is sufficiently high compared to the existing methods.
ER -