Designing subspecies of hardware trojans and their detection using neural network approach

Tomotaka Inoue, Kento Hasegawa, Yuki Kobayashi, Masao Yanagisawa, Nozomu Togawa

    研究成果: Conference contribution

    抄録

    Due to the recent technological development, home appliances and electric devices are equipped with high-performance hardware device. Since demand of hardware devices is increased, production base become internationalized to mass-produce hardware devices with low cost and hardware vendors outsource their products to third-party vendors. Accordingly, malicious third-party vendors can easily insert malfunctions (also known as 'hardware Trojans') into their products. In this paper, we design six kinds of hardware Trojans at a gate-level netlist, and apply a neural-network (NN) based hardware-Trojan detection method to them. The designed hardware Trojans are different in trigger circuits. In addition, we insert them to normal circuits, and detect hardware Trojans using a machine-learning-based hardware-Trojan detection method with neural networks. In our experiment, we learned Trojan-infected benchmarks using NN, and performed cross validation to evaluate the learned NN. The experimental results demonstrate that the average TPR (True Positive Rate) becomes 72.9%, the average TNR (True Negative Rate) becomes 90.0%.

    元の言語English
    ホスト出版物のタイトル2018 IEEE 8th International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2018
    出版者IEEE Computer Society
    2018-September
    ISBN(電子版)9781538660959
    DOI
    出版物ステータスPublished - 2018 12 13
    イベント8th IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2018 - Berlin, Germany
    継続期間: 2018 9 22018 9 5

    Other

    Other8th IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2018
    Germany
    Berlin
    期間18/9/218/9/5

    Fingerprint

    Neural networks
    Hardware
    Trigger circuits
    Domestic appliances
    Learning systems
    Networks (circuits)
    Costs
    Experiments
    Hardware security

    ASJC Scopus subject areas

    • Electrical and Electronic Engineering
    • Industrial and Manufacturing Engineering
    • Media Technology

    これを引用

    Inoue, T., Hasegawa, K., Kobayashi, Y., Yanagisawa, M., & Togawa, N. (2018). Designing subspecies of hardware trojans and their detection using neural network approach. : 2018 IEEE 8th International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2018 (巻 2018-September). [8576247] IEEE Computer Society. https://doi.org/10.1109/ICCE-Berlin.2018.8576247

    Designing subspecies of hardware trojans and their detection using neural network approach. / Inoue, Tomotaka; Hasegawa, Kento; Kobayashi, Yuki; Yanagisawa, Masao; Togawa, Nozomu.

    2018 IEEE 8th International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2018. 巻 2018-September IEEE Computer Society, 2018. 8576247.

    研究成果: Conference contribution

    Inoue, T, Hasegawa, K, Kobayashi, Y, Yanagisawa, M & Togawa, N 2018, Designing subspecies of hardware trojans and their detection using neural network approach. : 2018 IEEE 8th International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2018. 巻. 2018-September, 8576247, IEEE Computer Society, 8th IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2018, Berlin, Germany, 18/9/2. https://doi.org/10.1109/ICCE-Berlin.2018.8576247
    Inoue T, Hasegawa K, Kobayashi Y, Yanagisawa M, Togawa N. Designing subspecies of hardware trojans and their detection using neural network approach. : 2018 IEEE 8th International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2018. 巻 2018-September. IEEE Computer Society. 2018. 8576247 https://doi.org/10.1109/ICCE-Berlin.2018.8576247
    Inoue, Tomotaka ; Hasegawa, Kento ; Kobayashi, Yuki ; Yanagisawa, Masao ; Togawa, Nozomu. / Designing subspecies of hardware trojans and their detection using neural network approach. 2018 IEEE 8th International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2018. 巻 2018-September IEEE Computer Society, 2018.
    @inproceedings{475157f2e4604324af1e70417a7990ea,
    title = "Designing subspecies of hardware trojans and their detection using neural network approach",
    abstract = "Due to the recent technological development, home appliances and electric devices are equipped with high-performance hardware device. Since demand of hardware devices is increased, production base become internationalized to mass-produce hardware devices with low cost and hardware vendors outsource their products to third-party vendors. Accordingly, malicious third-party vendors can easily insert malfunctions (also known as 'hardware Trojans') into their products. In this paper, we design six kinds of hardware Trojans at a gate-level netlist, and apply a neural-network (NN) based hardware-Trojan detection method to them. The designed hardware Trojans are different in trigger circuits. In addition, we insert them to normal circuits, and detect hardware Trojans using a machine-learning-based hardware-Trojan detection method with neural networks. In our experiment, we learned Trojan-infected benchmarks using NN, and performed cross validation to evaluate the learned NN. The experimental results demonstrate that the average TPR (True Positive Rate) becomes 72.9{\%}, the average TNR (True Negative Rate) becomes 90.0{\%}.",
    keywords = "design time, gate-level netlist, hardware Trojan, machine learning, neural network",
    author = "Tomotaka Inoue and Kento Hasegawa and Yuki Kobayashi and Masao Yanagisawa and Nozomu Togawa",
    year = "2018",
    month = "12",
    day = "13",
    doi = "10.1109/ICCE-Berlin.2018.8576247",
    language = "English",
    volume = "2018-September",
    booktitle = "2018 IEEE 8th International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2018",
    publisher = "IEEE Computer Society",

    }

    TY - GEN

    T1 - Designing subspecies of hardware trojans and their detection using neural network approach

    AU - Inoue, Tomotaka

    AU - Hasegawa, Kento

    AU - Kobayashi, Yuki

    AU - Yanagisawa, Masao

    AU - Togawa, Nozomu

    PY - 2018/12/13

    Y1 - 2018/12/13

    N2 - Due to the recent technological development, home appliances and electric devices are equipped with high-performance hardware device. Since demand of hardware devices is increased, production base become internationalized to mass-produce hardware devices with low cost and hardware vendors outsource their products to third-party vendors. Accordingly, malicious third-party vendors can easily insert malfunctions (also known as 'hardware Trojans') into their products. In this paper, we design six kinds of hardware Trojans at a gate-level netlist, and apply a neural-network (NN) based hardware-Trojan detection method to them. The designed hardware Trojans are different in trigger circuits. In addition, we insert them to normal circuits, and detect hardware Trojans using a machine-learning-based hardware-Trojan detection method with neural networks. In our experiment, we learned Trojan-infected benchmarks using NN, and performed cross validation to evaluate the learned NN. The experimental results demonstrate that the average TPR (True Positive Rate) becomes 72.9%, the average TNR (True Negative Rate) becomes 90.0%.

    AB - Due to the recent technological development, home appliances and electric devices are equipped with high-performance hardware device. Since demand of hardware devices is increased, production base become internationalized to mass-produce hardware devices with low cost and hardware vendors outsource their products to third-party vendors. Accordingly, malicious third-party vendors can easily insert malfunctions (also known as 'hardware Trojans') into their products. In this paper, we design six kinds of hardware Trojans at a gate-level netlist, and apply a neural-network (NN) based hardware-Trojan detection method to them. The designed hardware Trojans are different in trigger circuits. In addition, we insert them to normal circuits, and detect hardware Trojans using a machine-learning-based hardware-Trojan detection method with neural networks. In our experiment, we learned Trojan-infected benchmarks using NN, and performed cross validation to evaluate the learned NN. The experimental results demonstrate that the average TPR (True Positive Rate) becomes 72.9%, the average TNR (True Negative Rate) becomes 90.0%.

    KW - design time

    KW - gate-level netlist

    KW - hardware Trojan

    KW - machine learning

    KW - neural network

    UR - http://www.scopus.com/inward/record.url?scp=85060285069&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85060285069&partnerID=8YFLogxK

    U2 - 10.1109/ICCE-Berlin.2018.8576247

    DO - 10.1109/ICCE-Berlin.2018.8576247

    M3 - Conference contribution

    AN - SCOPUS:85060285069

    VL - 2018-September

    BT - 2018 IEEE 8th International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2018

    PB - IEEE Computer Society

    ER -