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
Recentemente, foi relatado que fornecedores maliciosos de IC de terceiros frequentemente inserem trojans de hardware em seus produtos. Especialmente na etapa de design do IC, fornecedores terceirizados mal-intencionados podem facilmente inserir Trojans de hardware em seus produtos e, portanto, temos que detectá-los de forma eficiente. Neste artigo, propomos um método de detecção de Trojan de hardware baseado em aprendizado de máquina para netlists em nível de portão usando redes neurais multicamadas. Primeiro, extraímos 11 valores de recursos da Trojan-net para cada rede em uma netlist. Depois disso, classificamos as redes em uma netlist desconhecida em um conjunto de redes Trojan e de redes normais usando redes neurais multicamadas. Ao otimizar experimentalmente a estrutura das redes neurais multicamadas, podemos obter uma média de 84.8% de taxa de verdadeiro positivo e uma média de 70.1% de taxa de verdadeiro negativo, enquanto podemos obter 100% de taxa de verdadeiro positivo em alguns dos benchmarks, o que supera o métodos existentes na maioria dos casos.
Kento HASEGAWA
Waseda University
Masao YANAGISAWA
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.
Copiar
Kento HASEGAWA, Masao YANAGISAWA, Nozomu TOGAWA, "Empirical Evaluation and Optimization of Hardware-Trojan Classification for Gate-Level Netlists Based on Multi-Layer Neural Networks" in IEICE TRANSACTIONS on Fundamentals,
vol. E101-A, no. 12, pp. 2320-2326, December 2018, doi: 10.1587/transfun.E101.A.2320.
Abstract: Recently, it has been reported that malicious third-party IC vendors often insert hardware Trojans into their products. Especially in IC design step, malicious third-party vendors can easily insert hardware Trojans in their products and thus we have to detect them efficiently. 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. By experimentally optimizing the structure of multi-layer neural networks, we can obtain an average of 84.8% true positive rate and an average of 70.1% true negative rate while we can obtain 100% true positive rate in some of the benchmarks, which outperforms the existing methods in most of the cases.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E101.A.2320/_p
Copiar
@ARTICLE{e101-a_12_2320,
author={Kento HASEGAWA, Masao YANAGISAWA, Nozomu TOGAWA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Empirical Evaluation and Optimization of Hardware-Trojan Classification for Gate-Level Netlists Based on Multi-Layer Neural Networks},
year={2018},
volume={E101-A},
number={12},
pages={2320-2326},
abstract={Recently, it has been reported that malicious third-party IC vendors often insert hardware Trojans into their products. Especially in IC design step, malicious third-party vendors can easily insert hardware Trojans in their products and thus we have to detect them efficiently. 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. By experimentally optimizing the structure of multi-layer neural networks, we can obtain an average of 84.8% true positive rate and an average of 70.1% true negative rate while we can obtain 100% true positive rate in some of the benchmarks, which outperforms the existing methods in most of the cases.},
keywords={},
doi={10.1587/transfun.E101.A.2320},
ISSN={1745-1337},
month={December},}
Copiar
TY - JOUR
TI - Empirical Evaluation and Optimization of Hardware-Trojan Classification for Gate-Level Netlists Based on Multi-Layer Neural Networks
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2320
EP - 2326
AU - Kento HASEGAWA
AU - Masao YANAGISAWA
AU - Nozomu TOGAWA
PY - 2018
DO - 10.1587/transfun.E101.A.2320
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E101-A
IS - 12
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - December 2018
AB - Recently, it has been reported that malicious third-party IC vendors often insert hardware Trojans into their products. Especially in IC design step, malicious third-party vendors can easily insert hardware Trojans in their products and thus we have to detect them efficiently. 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. By experimentally optimizing the structure of multi-layer neural networks, we can obtain an average of 84.8% true positive rate and an average of 70.1% true negative rate while we can obtain 100% true positive rate in some of the benchmarks, which outperforms the existing methods in most of the cases.
ER -