A Hardware Trojan Detection Method Design Based on TensorFlow

  • Wenzhi WuEmail author
  • Ying Wei
  • Ruizhe Ye
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11910)


As an extra circuit inserted into chip design, Hardware Trojan can achieve malicious functional changes, reliability reduction or secret information disclosure. Meanwhile, the design of the hardware Trojan circuit is concealed, triggered only under rare conditions, and is in a waiting state for most of the life cycle. It is quite small compared to the host design and has little influence on circuit parameters. Therefore, it is difficult to detect hardware Trojans. Fast and accurate detection technology is provided by Google’s open source machine learning framework TensorFlow. The hardware Trojan circuit adopts the standard circuit provided by Trust-Hub. It is realized through FPGA programming. ISE is used for compiling and simulation to obtain the characteristic value of the circuit; Finally, a hardware Trojan detection platform based on machine learning is established by simulating the data via TensorFlow machine learning. The experimental test results verify the correctness of the design and provide a simple hardware Trojan detection for IC.


Hardware Trojan Detection TensorFlow Machine learning FPGA 


  1. 1.
    Lei, Z., Mengxi, Y., Chaoen, X., Youheng, D.: Hardware Trojan detection based on optimized SVM algorithm. Appl. Electron. Tech. 44(11), 17–20 (2018)Google Scholar
  2. 2.
    Liang, W., et al.: A security situation prediction algorithm based on HMM in mobile network. WCMC 2018(4), 1–11 (2018)Google Scholar
  3. 3.
    Liang, W., et al.: Efficient data packet transmission algorithm for IPV6 mobile vehicle network based on fast switching model with time difference. FGCS 100, 132–143 (2019)CrossRefGoogle Scholar
  4. 4.
    Liang, W., Long, J., Weng, T.H., Chen, X., Li, K.C., Zomaya, A.Y.: TBRS: a trust based recommendation scheme for vehicular CPS. FGCS 92, 383–398 (2019)CrossRefGoogle Scholar
  5. 5.
    Cakir, B., Malik, S.: Hardware Trojan detection for gate-level ICs using signal correlation based clustering. In: Proceedings Design, Automation and Test in Europe (DATE), p. 47147 (2015)Google Scholar
  6. 6.
    Xue, M., Bian, R., Liu, W., et al.: Defeating untrustworthy testing parties: a novel hybrid clustering ensemble based golden models-free hardware Trojan detection method. IEEE Access 7, 5124–5140 (2018)CrossRefGoogle Scholar
  7. 7.
    Dong, C., He, G., Liu, X., et al.: A multi-layer hardware trojan protection framework for IoT chips. IEEE Access 7, 23628–23639 (2019)CrossRefGoogle Scholar
  8. 8.
    Hasegawa, K., Yanagisawa, M., Togawa, N.: Hardware Trojans classification for gate-level netlists using multi-layer neural networks. In: 2017 IEEE 23rd International Symposium on On-Line Testing and Robust System Design (IOLTS). IEEE, pp. 227–232 (2017)Google Scholar
  9. 9.
    Hasegawa, K., Yanagisawa, M.: A hardware-Trojan classification classification method using machine learning at gate-level netlists based on Trojan features. IEEE (2017)Google Scholar
  10. 10.
    Lin, N., Lei, S., Kun, H., Shaoqing, L.: Hardware Trojan detection of IP soft cores based on feature matching. Comput. Eng. 43(03), 176–180 (2017)Google Scholar
  11. 11.
    Salmani, H., Tehranipoor, M., Karri, R.: On design vulnerability analysis and trust benchmarks development. In: 2013 IEEE 31st International Conference on Computer Design (ICCD). IEEE, pp. 471–474 (2013)Google Scholar
  12. 12.
    Shakya, B., He, T., Salmani, H., Forte, D., Bhunia, S., Tehranipoor, M.: Benchmarking of hardware Trojans and maliciously affected circuits. J. Hardw. Syst. Secur. (HaSS) 1, 85–102 (2017)CrossRefGoogle Scholar
  13. 13.
    FIFO Generator v13.2 LogiCORE IP Product Guide. Xilinx (2017).
  14. 14.
    Chang Zhanguo, P., Baoming, L.X., Shuai, W., Shuo, Y.: Automatic detection of myocardial infarction via machine learning. Comput. Syst. Appl. 04, 218–224 (2019)Google Scholar
  15. 15.
    Fangyu, R., Yang, X., Siyuan, Z., Renyuan, H.: Research on remote sensing image feature recognition based on TensorFlow. Sci. Technol. Innov. Her. 15(11), 53–54 (2018)Google Scholar
  16. 16.
    Huang Rui, L., Yilin, X.W.: Handwritten digital recognition and application based on TensorFlow deep learning. Appl. Electron. Tech. 44(10), 6–10 (2018)Google Scholar
  17. 17.
    Gavai, N.R., Jakhade, Y.A., Tribhuvan, S.A., et al.: MobileNets for flower classification using TensorFlow. In: 2017 International Conference on Big Data, IoT and Data Science (BID), pp. 154–158. IEEE (2017)Google Scholar
  18. 18.
    Saxena, A.: Convolutional neural networks: an illustration in TensorFlow. XRDS: Crossroads ACM Mag. Stud. 22(4), 56–58 (2016)MathSciNetCrossRefGoogle Scholar
  19. 19.
    Thakur, K., Qiu, M., Gai, K., et al.: An investigation on cyber security threats and security models. In: 2015 IEEE 2nd International Conference on Cyber Security and Cloud Computing. IEEE, pp. 307–311 (2015)Google Scholar
  20. 20.
    Gai, K., Qiu, M., Elnagdy, S.A.: Security-aware information classifications using supervised learning for cloud-based cyber risk management in financial big data. In: 2016 IEEE 2nd International Conference on Big Data Security on Cloud (BigDataSecurity), IEEE International Conference on High Performance and Smart Computing (HPSC), and IEEE International Conference on Intelligent Data and Security (IDS), pp. 197–202. IEEE (2016)Google Scholar
  21. 21.
    Qiu, H., Qiu, M., LU, Z., et al.: An efficient key distribution system for data fusion in V2X heterogeneous networks. Inf. Fusion 50, 212–220 (2019)CrossRefGoogle Scholar
  22. 22.
    Qiu, H., Kapusta, K., Lu, Z., et al.: All-Or-Nothing data protection for ubiquitous communication: challenges and perspectives. Inf. Sci. (2019)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Network Information CenterXiamen University of TechnologyXiamenChina
  2. 2.Xiamen University Tan Kah Kee CollegeXiamenChina
  3. 3.Engineering Research Center for Software Testing and Evaluation of Fujian ProvinceXiamenChina

Personalised recommendations