Designing hardware trojans and their detection based on a SVM-based approach

Tomotaka Inoue, Kento Hasegawa, Masao Yanagisawa, Nozomu Togawa

    研究成果: Conference contribution

    6 引用 (Scopus)

    抄録

    Since hardware production become inexpensive and international, hardware vendors often outsource their products to third-party vendors. Due to the situation, malicious vendors can easily insert malfunctions (also known as 'hardware Trojans') to their products. In this paper, we experimentally evaluate a machine-learning-based hardware-Trojan detection method using several hardware Trojans we designed. To begin with, we design three types of hardware Trojans and insert them to simple RS232 transceiver circuits. After that, we learn known netlists, where we know which nets are Trojan ones or normal ones beforehand, using a machine-learning-based hardware-Trojan detection method with a support vector machine (SVM) classifier. Finally, we classify the nets in the designed hardware-Trojan-inserted netlists into a set of Trojan nets and that of normal nets using the learned classifier. The experimental results demonstrate that the hardware-Trojan detection method with the SVM-based approach can detect a part of hardware Trojans we designed.

    元の言語English
    ホスト出版物のタイトルProceedings - 2017 IEEE 12th International Conference on ASIC, ASICON 2017
    出版者IEEE Computer Society
    ページ811-814
    ページ数4
    2017-October
    ISBN(電子版)9781509066247
    DOI
    出版物ステータスPublished - 2018 1 8
    イベント12th IEEE International Conference on Advanced Semiconductor Integrated Circuits, ASICON 2017 - Guiyang, China
    継続期間: 2017 10 252017 10 28

    Other

    Other12th IEEE International Conference on Advanced Semiconductor Integrated Circuits, ASICON 2017
    China
    Guiyang
    期間17/10/2517/10/28

    Fingerprint

    Support vector machines
    Hardware
    Learning systems
    Classifiers
    Transceivers
    Hardware security
    Networks (circuits)

    ASJC Scopus subject areas

    • Hardware and Architecture
    • Electrical and Electronic Engineering

    これを引用

    Inoue, T., Hasegawa, K., Yanagisawa, M., & Togawa, N. (2018). Designing hardware trojans and their detection based on a SVM-based approach. : Proceedings - 2017 IEEE 12th International Conference on ASIC, ASICON 2017 (巻 2017-October, pp. 811-814). IEEE Computer Society. https://doi.org/10.1109/ASICON.2017.8252600

    Designing hardware trojans and their detection based on a SVM-based approach. / Inoue, Tomotaka; Hasegawa, Kento; Yanagisawa, Masao; Togawa, Nozomu.

    Proceedings - 2017 IEEE 12th International Conference on ASIC, ASICON 2017. 巻 2017-October IEEE Computer Society, 2018. p. 811-814.

    研究成果: Conference contribution

    Inoue, T, Hasegawa, K, Yanagisawa, M & Togawa, N 2018, Designing hardware trojans and their detection based on a SVM-based approach. : Proceedings - 2017 IEEE 12th International Conference on ASIC, ASICON 2017. 巻. 2017-October, IEEE Computer Society, pp. 811-814, 12th IEEE International Conference on Advanced Semiconductor Integrated Circuits, ASICON 2017, Guiyang, China, 17/10/25. https://doi.org/10.1109/ASICON.2017.8252600
    Inoue T, Hasegawa K, Yanagisawa M, Togawa N. Designing hardware trojans and their detection based on a SVM-based approach. : Proceedings - 2017 IEEE 12th International Conference on ASIC, ASICON 2017. 巻 2017-October. IEEE Computer Society. 2018. p. 811-814 https://doi.org/10.1109/ASICON.2017.8252600
    Inoue, Tomotaka ; Hasegawa, Kento ; Yanagisawa, Masao ; Togawa, Nozomu. / Designing hardware trojans and their detection based on a SVM-based approach. Proceedings - 2017 IEEE 12th International Conference on ASIC, ASICON 2017. 巻 2017-October IEEE Computer Society, 2018. pp. 811-814
    @inproceedings{2ba47fd7be854b0b90978d6f91865921,
    title = "Designing hardware trojans and their detection based on a SVM-based approach",
    abstract = "Since hardware production become inexpensive and international, hardware vendors often outsource their products to third-party vendors. Due to the situation, malicious vendors can easily insert malfunctions (also known as 'hardware Trojans') to their products. In this paper, we experimentally evaluate a machine-learning-based hardware-Trojan detection method using several hardware Trojans we designed. To begin with, we design three types of hardware Trojans and insert them to simple RS232 transceiver circuits. After that, we learn known netlists, where we know which nets are Trojan ones or normal ones beforehand, using a machine-learning-based hardware-Trojan detection method with a support vector machine (SVM) classifier. Finally, we classify the nets in the designed hardware-Trojan-inserted netlists into a set of Trojan nets and that of normal nets using the learned classifier. The experimental results demonstrate that the hardware-Trojan detection method with the SVM-based approach can detect a part of hardware Trojans we designed.",
    keywords = "Design time, Gate-level netlist, Hardware Trojan, Machine learning, Support vector machine",
    author = "Tomotaka Inoue and Kento Hasegawa and Masao Yanagisawa and Nozomu Togawa",
    year = "2018",
    month = "1",
    day = "8",
    doi = "10.1109/ASICON.2017.8252600",
    language = "English",
    volume = "2017-October",
    pages = "811--814",
    booktitle = "Proceedings - 2017 IEEE 12th International Conference on ASIC, ASICON 2017",
    publisher = "IEEE Computer Society",

    }

    TY - GEN

    T1 - Designing hardware trojans and their detection based on a SVM-based approach

    AU - Inoue, Tomotaka

    AU - Hasegawa, Kento

    AU - Yanagisawa, Masao

    AU - Togawa, Nozomu

    PY - 2018/1/8

    Y1 - 2018/1/8

    N2 - Since hardware production become inexpensive and international, hardware vendors often outsource their products to third-party vendors. Due to the situation, malicious vendors can easily insert malfunctions (also known as 'hardware Trojans') to their products. In this paper, we experimentally evaluate a machine-learning-based hardware-Trojan detection method using several hardware Trojans we designed. To begin with, we design three types of hardware Trojans and insert them to simple RS232 transceiver circuits. After that, we learn known netlists, where we know which nets are Trojan ones or normal ones beforehand, using a machine-learning-based hardware-Trojan detection method with a support vector machine (SVM) classifier. Finally, we classify the nets in the designed hardware-Trojan-inserted netlists into a set of Trojan nets and that of normal nets using the learned classifier. The experimental results demonstrate that the hardware-Trojan detection method with the SVM-based approach can detect a part of hardware Trojans we designed.

    AB - Since hardware production become inexpensive and international, hardware vendors often outsource their products to third-party vendors. Due to the situation, malicious vendors can easily insert malfunctions (also known as 'hardware Trojans') to their products. In this paper, we experimentally evaluate a machine-learning-based hardware-Trojan detection method using several hardware Trojans we designed. To begin with, we design three types of hardware Trojans and insert them to simple RS232 transceiver circuits. After that, we learn known netlists, where we know which nets are Trojan ones or normal ones beforehand, using a machine-learning-based hardware-Trojan detection method with a support vector machine (SVM) classifier. Finally, we classify the nets in the designed hardware-Trojan-inserted netlists into a set of Trojan nets and that of normal nets using the learned classifier. The experimental results demonstrate that the hardware-Trojan detection method with the SVM-based approach can detect a part of hardware Trojans we designed.

    KW - Design time

    KW - Gate-level netlist

    KW - Hardware Trojan

    KW - Machine learning

    KW - Support vector machine

    UR - http://www.scopus.com/inward/record.url?scp=85044751081&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85044751081&partnerID=8YFLogxK

    U2 - 10.1109/ASICON.2017.8252600

    DO - 10.1109/ASICON.2017.8252600

    M3 - Conference contribution

    AN - SCOPUS:85044751081

    VL - 2017-October

    SP - 811

    EP - 814

    BT - Proceedings - 2017 IEEE 12th International Conference on ASIC, ASICON 2017

    PB - IEEE Computer Society

    ER -