指令级功耗特征的硬件木马检测高效机器学习

doi:10.7523/j.issn.2095-6134.2021.04.008

中国科学院大学学报 ›› 2021, Vol. 38 ›› Issue (4): 494-502.DOI: 10.7523/j.issn.2095-6134.2021.04.008

指令级功耗特征的硬件木马检测高效机器学习

李莹¹, 陈岚^1,2, 佟鑫¹

1. 中国科学院微电子研究所, 北京 1000;
2. 三维及纳米集成电路设计自动化技术北京市重点实验室, 北京 100029

收稿日期:2019-09-26 修回日期:2019-11-22 发布日期:2021-07-10
通讯作者: 陈岚
基金资助:
Supported by Beijing Natural Science Foundation (4184106), National Internet of Things and Smart City Key Project Docking (Z181100003518002), Beijing Science and Technology Project (Z171100001117147)

Efficient machine learning methods for hardware Trojan detection using instruction-level power character

LI Ying¹, CHEN Lan^1,2, TONG Xin¹

1. Institute of Microelectronics, Chinese Academy of Sciences, Beijing 100029, China;
2. Beijing Key Laboratory of Three-dimensional and Nanometer Integrated Circuit Design Automation Technology, Beijing 100029, China

Received:2019-09-26 Revised:2019-11-22 Published:2021-07-10
Supported by:
Supported by Beijing Natural Science Foundation (4184106), National Internet of Things and Smart City Key Project Docking (Z181100003518002), Beijing Science and Technology Project (Z171100001117147)

摘要/Abstract

摘要： 由于半导体产业的设计和外包代工制造全球化趋势，使得集成电路容易受到硬件木马造成的严峻威胁。基于电路退化模型等的隐秘硬件木马通常将恶意行为隐藏在正常的芯片行为中，从而难以被传统的测试和验证方法发现。建立一个高效的机器学习框架，利用指令级侧信道功耗特征对无木马和插入木马的芯片电路进行分类。算法模型采用不同的指令和木马构造提取的特征向量集。为评估检测方法性能，在Altera Stratix Ⅱ FPGA中实现基于MC8051微控制器的基准电路，并详细分析在有监督和无监督模式下的5种机器学习算法模型。测试结果表明，综合各种特征条件，有监督的朴素贝叶斯方法检测准确率最高，平均为95%，有监督的支持向量机方法运行时间最短，平均为0.04 s。另外验证了无监督的支持向量机可以作为一种没有黄金参考模型下的有价值方法，即使在恶劣训练条件下，其检测准确率也在17%~72%。

关键词: 硬件木马, 机器学习, 旁路功耗, 指令级, 检测

Abstract: Integrated circuits (IC) are vulnerable to hardware Trojans (HTs) due to the globalization of semiconductor design and outsourcing fabrication. Stealthy HTs which activate malicious aging operations are ususlly hide in normal behaviors.Therefore, it is a challenge to detect those HTs by general test and verification approaches. In this paper, we build an efficient machine learning (ML) framework to classify the genuine and Trojan-insert chips using instruction-level side-channel power characters. Different instructions and HTs are used as feature sets to construct the algorithm models. In order to evaluate the performance of the method, we implemented five HTs benchmarks of MC8051 micro-controller in Altera Stratix II FPGA, and presented analysis on five formulated ML models in both supervised and unsupervised modes. The test results showed that the detection accuracy of supervised Naïve Bayes is 95% in average, which is the highest among the ML models. The supervised SVM consumed the shortest running time, with an average of 0.04 s. We also verified that one-class SVM can be a valuable method without golden reference, which has accuracy in the range from 17% to 72% even in Harsh learning condition.

Key words: hardware Trojans, machine learning, side-channel power, instruction-level, detection

中图分类号:

TN406

李莹, 陈岚, 佟鑫. 指令级功耗特征的硬件木马检测高效机器学习[J]. 中国科学院大学学报, 2021, 38(4): 494-502.

LI Ying, CHEN Lan, TONG Xin. Efficient machine learning methods for hardware Trojan detection using instruction-level power character[J]. Journal of University of Chinese Academy of Sciences, 2021, 38(4): 494-502.

参考文献

[1] Tehranipoor M, Koushanfar F. A survey of hardware Trojan taxonomy & detection[J]. IEEE Design & Test of Computers, 2010, 27(1):10-25.
[2] Rad R, Plusquellic J, Tehranipoor M. Sensitivity analysis to hardware Trojans using power supply transient signals[C]//2018 IEEE International Workshop on Hardware-Oriented Security and Trust. Anaheim,CA,USA:IEEE Press, 2008:3-7.
[3] Hou B, He C H, Wang L W, et al. Hardware Trojan detection via current measurement:a method immune to process variation effects[C]//201410th International Conference on Reliability,Maintainability and Safely(ICRMS). Guangzhou:IEEE Press, 2015:1039-1042.
[4] Aarestad J, Acharyya D, Rad R, et al. Detecting Trojans through leakage current analysis using multiple supply pad I_DDQs[J]. IEEE Transactions on Information Forensics and Security, 2010, 5(4):893-904.
[5] He J J, Zhao Y Q, Guo X L, et al. Hardware Trojan detection through chip-free electromagnetic side-channel statistical analysis[J]. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2017,25(10):2939-2948.
[6] Koushanfar F, Potkonjak M. CAD-based security, cryptography, and digital rights management[C]//200744th ACM/IEEE Design Automation Conference. San Diego,CA,USA:IEEE Press, 2007:268-269.
[7] Wei S, Potkonjak M. Scalable consistency-based hardware Trojan detection and diagnosis[C]//20115th IEEE International Conference on Network and System Security. Milan,Italy:IEEE Press, 2011:176-183.
[8] Liu Y, Jin Y E, Nosratinia A, et al. Silicon demonstration of hardware Trojan design and detection in wireless cryptographic ICs[J]. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2017, 25(4):1506-1519.
[9] Karimi N, Kanuparthi A K, Wang X Y, et al. MAGIC:malicious aging in circuits/cores[J]. ACM Transactions on Architecture and Code Optimization, 2015, 12(1):1-25.
[10] Wang X X, Tehranipoor M, Plusquellic J. Detecting malicious inclusions in secure hardware:challenges and solutions[C]//2008 IEEE International Workshop on Hardware-Oriented Security and Trust. Anaheim,CA,USA:IEEE Press, 2008:15-19.
[11] Chakraborty R S, Wolff F, Paul S, et al. MERO:A statistical approach for hardware Trojan detection[C]//11th International Workshop on Cryptographic Hardware and Embedded Systems. Lansanne, Switzerland:Springer, 2009:396-410.
[12] Rai D, Lach J. Performance of delay-based Trojan detection techniques under parameter variations[C]//2009 IEEE International Workshop on Hardware-Oriented Security and Trust. San Francisco,CA,USA:IEEE Press, 2009:58-65.
[13] Li X, Wang X, Zhang Y, et al. Hardware trojan detection method based on multiple side-channels analysis[J]. Computer Simulation, 2015, 32(3):216-219.(in Chinese).
[14] Narasimhan S, Du D D, Chakraborty R S, et al. Hardware trojan detection by multiple-parameter side-channel analysis[J]. IEEE Transactions on Computers, 2013, 62(11):2183-2195.
[15] Salmani H, Tehranipoor M, Plusquellic J. A layout-aware approach for improving localized switching to detect hardware Trojans in integrated circuits[C]//2010 IEEE International Workshop on Information Forensics and Security. Seattle,WA,USA:IEEE Press, 2010:1-6.
[16] Forte D, Bao C X, Srivastava A. Temperature tracking:An innovative run-time approach for hardware Trojan detection[C]//2013 IEEEE/ACM International Conference on Computer-Aided Design(ICCAD). San Jose,CA,USA:IEEE Press, 2013:532-539.
[17] Zhao H, Kwiat K, Kamhoua C, et al. Applying chaos theory for runtime Hardware Trojan detection[C]//2015 IEEE Symposium on Computational Intelligence for Security and Defense Applications(CISDA). Verona, NY, USA:IEEE Press, 2015:1-6.
[18] Jap D, He W, Bhasin S. Supervised and unsupervised machine learning for side-channel based Trojan detection[C]//2016 IEEE 27th International Conference on Application-specific Systems, Architectures and Processors (ASAP). London,UK:IEEE Press, 2016:17-24.
[19] Bao C X, Forte D, Srivastava A. On reverse engineering-based hardware Trojan detection[J]. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2016, 35(1):49-57.
[20] Lodhi F K, Abbasi I, Khalid F, et al. A self-learning framework to detect the intruded integrated circuits[C]//2016 IEEE International Symposium on Circuits and System(ISCAS). Montreal,QC,Canada:IEEE Press, 2016:1702-1705.
[21] Xue M F, Wang J, Hux A Q. An enhanced classification-based golden chips-free hardware Trojan detection technique[C]//2016 IEEE Asian Hardware-Oriented Security and Trust (AsianHOST). Yilan,Taiwan,China:IEEE Press, 2016:1-6.
[22] Inoue T, Hasegawa K, Yanagisawa M, et al. Designing hardware Trojans and their detection based on a SVM-based approach[C]//2017 IEEE 12th International Conference on ASIC (ASICON). Guiyang,China:IEEE Press, 2017:811-814.
[23] Lodhi F K, Hasan S R, Hasan O, et al. Power profiling of microcontroller's instruction set for runtime hardware Trojans detection without golden circuit models[C]//Design, Automation & Test in Europe Conference & Exhibition(DATE),2017. Lausanne,Switzerland:IEEE Press, 2017:294-297.
[24] Mazidi M A, Mazidi J G, Mckinlay R D. The 8051 microcontroller and embedded systems using assembly and C[M]. 2nd ed. New Jersey:PearsonEducation, 2007.
[25] Tehranipoor M, Salamani H. trust-HUB.[CP/OL]. (2006-03-06)[2019-11-11]. https://www.trust-hub.org/.
[26] Chang C C, Lin C J. LIBSVM:A library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology, 2011, 2(3):1-27.

指令级功耗特征的硬件木马检测高效机器学习

Efficient machine learning methods for hardware Trojan detection using instruction-level power character

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

访问统计

联系我们

[1]	王晓辉, 胡玉新, 吕鹏. 基于显著图融合的高分四号卫星光学遥感图像多运动舰船检测方法[J]. 中国科学院大学学报, 2021, 38(5): 649-659.
[2]	席彦新, 计璐艳, 耿修瑞. 一种多时相遥感图像多目标检测算法[J]. 中国科学院大学学报, 2021, 38(4): 503-510.
[3]	兰云, 唐亮, 卜智勇, 曹乐搬. 非均匀杂波背景下MIMO雷达扩展目标自适应检测器[J]. 中国科学院大学学报, 2021, 38(4): 524-531.
[4]	王琳, 陈熙霖. 基于高斯层级损失的开放场景物体检测[J]. 中国科学院大学学报, 2021, 38(4): 538-548.
[5]	宋志华, 陈锟山, 曾江源, 许镇. 一种基于FMCW雷达的慢速目标检测自适应滤波器[J]. 中国科学院大学学报, 2021, 38(3): 382-391.
[6]	黄萍萍, 王峰, 向俞明, 尤红建. 基于V-CSK视频遥感卫星运动目标检测跟踪方法[J]. 中国科学院大学学报, 2021, 38(3): 392-401.
[7]	孙宇豪, 李国通, 张鸽. 一种基于相关概率模型的卫星异常检测方法[J]. 中国科学院大学学报, 2021, 38(3): 409-416.
[8]	张苏, 齐立忠, 韩文军, 朱笑笑, 习晓环, 王成, 王濮, 聂胜. 基于无人机激光点云的树障检测与砍伐树木数量估算[J]. 中国科学院大学学报, 2020, 37(6): 760-766.
[9]	余保玲, 虞松坤, 孙耀然, 杨振, 傅旭波. 基于DeepPose和Faster RCNN的多目标人体骨骼节点检测算法[J]. 中国科学院大学学报, 2020, 37(6): 828-834.
[10]	李森, 彭玲, 胡媛, 池天河. 基于FD-RCF的高分辨率遥感影像耕地边缘检测[J]. 中国科学院大学学报, 2020, 37(4): 483-489.
[11]	陈国炜, 刘磊, 郭嘉逸, 潘宗序, 胡文龙. 基于生成对抗网络的半监督遥感图像飞机检测[J]. 中国科学院大学学报, 2020, 37(4): 539-546.
[12]	赖训飞, 梁旭文, 谢卓辰, 李宗旺. 基于实体嵌入和长短时记忆网络的入侵检测方法[J]. 中国科学院大学学报, 2020, 37(4): 553-561.
[13]	孙铭堃, 梁令羽, 汪涵, 何为, 赵鲁阳. 基于级联卷积网络的面部关键点定位算法[J]. 中国科学院大学学报, 2020, 37(4): 562-569.
[14]	赵择, 徐佑宇, 唐亮, 卜智勇. 基于改进一对一算法的网络流量分类[J]. 中国科学院大学学报, 2020, 37(4): 570-576.
[15]	卢凯旋, 李国清, 陈正超, 昝露洋, 李柏鹏, 高建威. 基于负样本多通道优化SSD网络的钢铁厂提取[J]. 中国科学院大学学报, 2020, 37(3): 352-359.