Hardware Trojans classification for gate-level netlists based on machine learning

Kento Hasegawa, Masaru Oya, Masao Yanagisawa, Nozomu Togawa

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    22 Citations (Scopus)

    Abstract

    Recently, we face a serious risk that malicious third-party vendors can very easily insert hardware Trojans into their IC products but it is very difficult to analyze huge and complex ICs. In this paper, we propose a hardware-Trojan classification method to identify hardware-Trojan infected nets (or Trojan nets) using a support vector machine (SVM). Firstly, we extract the five hardware-Trojan features in each net in a netlist. Secondly, since we cannot effectively give the simple and fixed threshold values to them to detect hardware Trojans, we represent them to be a five-dimensional vector and learn them by using SVM. Finally, we can successfully classify a set of all the nets in an unknown netlist into Trojan ones and normal ones based on the learned SVM classifier. We have applied our SVM-based hardware-Trojan classification method to Trust-HUB benchmarks and the results demonstrate that our method can much increase the true positive rate compared to the existing state-of-the-art results in most of the cases. In some cases, our method can achieve the true positive rate of 100%, which shows that all the Trojan nets in a netlist are completely detected by our method.

    Original languageEnglish
    Title of host publication2016 IEEE 22nd International Symposium on On-Line Testing and Robust System Design, IOLTS 2016
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages203-206
    Number of pages4
    ISBN (Electronic)9781509015061
    DOIs
    Publication statusPublished - 2016 Oct 20
    Event22nd IEEE International Symposium on On-Line Testing and Robust System Design, IOLTS 2016 - Sant Feliu de Guixols, Catalunya, Spain
    Duration: 2016 Jul 42016 Jul 6

    Other

    Other22nd IEEE International Symposium on On-Line Testing and Robust System Design, IOLTS 2016
    CountrySpain
    CitySant Feliu de Guixols, Catalunya
    Period16/7/416/7/6

    Fingerprint

    Support vector machines
    Learning systems
    Hardware
    Classifiers
    Hardware security

    Keywords

    • gate-level netlist
    • hardware Trojan
    • machine learning
    • static detection
    • support vector machine (SVM)

    ASJC Scopus subject areas

    • Hardware and Architecture
    • Safety, Risk, Reliability and Quality
    • Computer Networks and Communications

    Cite this

    Hasegawa, K., Oya, M., Yanagisawa, M., & Togawa, N. (2016). Hardware Trojans classification for gate-level netlists based on machine learning. In 2016 IEEE 22nd International Symposium on On-Line Testing and Robust System Design, IOLTS 2016 (pp. 203-206). [7604700] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IOLTS.2016.7604700

    Hardware Trojans classification for gate-level netlists based on machine learning. / Hasegawa, Kento; Oya, Masaru; Yanagisawa, Masao; Togawa, Nozomu.

    2016 IEEE 22nd International Symposium on On-Line Testing and Robust System Design, IOLTS 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 203-206 7604700.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Hasegawa, K, Oya, M, Yanagisawa, M & Togawa, N 2016, Hardware Trojans classification for gate-level netlists based on machine learning. in 2016 IEEE 22nd International Symposium on On-Line Testing and Robust System Design, IOLTS 2016., 7604700, Institute of Electrical and Electronics Engineers Inc., pp. 203-206, 22nd IEEE International Symposium on On-Line Testing and Robust System Design, IOLTS 2016, Sant Feliu de Guixols, Catalunya, Spain, 16/7/4. https://doi.org/10.1109/IOLTS.2016.7604700
    Hasegawa K, Oya M, Yanagisawa M, Togawa N. Hardware Trojans classification for gate-level netlists based on machine learning. In 2016 IEEE 22nd International Symposium on On-Line Testing and Robust System Design, IOLTS 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 203-206. 7604700 https://doi.org/10.1109/IOLTS.2016.7604700
    Hasegawa, Kento ; Oya, Masaru ; Yanagisawa, Masao ; Togawa, Nozomu. / Hardware Trojans classification for gate-level netlists based on machine learning. 2016 IEEE 22nd International Symposium on On-Line Testing and Robust System Design, IOLTS 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 203-206
    @inproceedings{b92324f97a4f405a896c5899d30b3022,
    title = "Hardware Trojans classification for gate-level netlists based on machine learning",
    abstract = "Recently, we face a serious risk that malicious third-party vendors can very easily insert hardware Trojans into their IC products but it is very difficult to analyze huge and complex ICs. In this paper, we propose a hardware-Trojan classification method to identify hardware-Trojan infected nets (or Trojan nets) using a support vector machine (SVM). Firstly, we extract the five hardware-Trojan features in each net in a netlist. Secondly, since we cannot effectively give the simple and fixed threshold values to them to detect hardware Trojans, we represent them to be a five-dimensional vector and learn them by using SVM. Finally, we can successfully classify a set of all the nets in an unknown netlist into Trojan ones and normal ones based on the learned SVM classifier. We have applied our SVM-based hardware-Trojan classification method to Trust-HUB benchmarks and the results demonstrate that our method can much increase the true positive rate compared to the existing state-of-the-art results in most of the cases. In some cases, our method can achieve the true positive rate of 100{\%}, which shows that all the Trojan nets in a netlist are completely detected by our method.",
    keywords = "gate-level netlist, hardware Trojan, machine learning, static detection, support vector machine (SVM)",
    author = "Kento Hasegawa and Masaru Oya and Masao Yanagisawa and Nozomu Togawa",
    year = "2016",
    month = "10",
    day = "20",
    doi = "10.1109/IOLTS.2016.7604700",
    language = "English",
    pages = "203--206",
    booktitle = "2016 IEEE 22nd International Symposium on On-Line Testing and Robust System Design, IOLTS 2016",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",
    address = "United States",

    }

    TY - GEN

    T1 - Hardware Trojans classification for gate-level netlists based on machine learning

    AU - Hasegawa, Kento

    AU - Oya, Masaru

    AU - Yanagisawa, Masao

    AU - Togawa, Nozomu

    PY - 2016/10/20

    Y1 - 2016/10/20

    N2 - Recently, we face a serious risk that malicious third-party vendors can very easily insert hardware Trojans into their IC products but it is very difficult to analyze huge and complex ICs. In this paper, we propose a hardware-Trojan classification method to identify hardware-Trojan infected nets (or Trojan nets) using a support vector machine (SVM). Firstly, we extract the five hardware-Trojan features in each net in a netlist. Secondly, since we cannot effectively give the simple and fixed threshold values to them to detect hardware Trojans, we represent them to be a five-dimensional vector and learn them by using SVM. Finally, we can successfully classify a set of all the nets in an unknown netlist into Trojan ones and normal ones based on the learned SVM classifier. We have applied our SVM-based hardware-Trojan classification method to Trust-HUB benchmarks and the results demonstrate that our method can much increase the true positive rate compared to the existing state-of-the-art results in most of the cases. In some cases, our method can achieve the true positive rate of 100%, which shows that all the Trojan nets in a netlist are completely detected by our method.

    AB - Recently, we face a serious risk that malicious third-party vendors can very easily insert hardware Trojans into their IC products but it is very difficult to analyze huge and complex ICs. In this paper, we propose a hardware-Trojan classification method to identify hardware-Trojan infected nets (or Trojan nets) using a support vector machine (SVM). Firstly, we extract the five hardware-Trojan features in each net in a netlist. Secondly, since we cannot effectively give the simple and fixed threshold values to them to detect hardware Trojans, we represent them to be a five-dimensional vector and learn them by using SVM. Finally, we can successfully classify a set of all the nets in an unknown netlist into Trojan ones and normal ones based on the learned SVM classifier. We have applied our SVM-based hardware-Trojan classification method to Trust-HUB benchmarks and the results demonstrate that our method can much increase the true positive rate compared to the existing state-of-the-art results in most of the cases. In some cases, our method can achieve the true positive rate of 100%, which shows that all the Trojan nets in a netlist are completely detected by our method.

    KW - gate-level netlist

    KW - hardware Trojan

    KW - machine learning

    KW - static detection

    KW - support vector machine (SVM)

    UR - http://www.scopus.com/inward/record.url?scp=84997530270&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84997530270&partnerID=8YFLogxK

    U2 - 10.1109/IOLTS.2016.7604700

    DO - 10.1109/IOLTS.2016.7604700

    M3 - Conference contribution

    AN - SCOPUS:84997530270

    SP - 203

    EP - 206

    BT - 2016 IEEE 22nd International Symposium on On-Line Testing and Robust System Design, IOLTS 2016

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -