基于深度学习LSTM的侧信道分析

doi:10.19678/j.issn.1000-3428.0059210

计算机工程 ›› 2021, Vol. 47 ›› Issue (10): 140-146. doi: 10.19678/j.issn.1000-3428.0059210

基于深度学习LSTM的侧信道分析

王俊年^1,3, 朱斌^1,3, 于文新^2,3, 王皖^1,3, 胡钒梁^1,3

1. 湖南科技大学物理与电子科学学院, 湖南湘潭 411201;
2. 湖南科技大学信息与电气工程学院, 湖南湘潭 411201;
3. 知识处理与网络化制造湖南省普通高等学校重点实验室, 湖南湘潭 411201

收稿日期:2020-08-10 修回日期:2020-10-21 发布日期:2020-11-05
作者简介:王俊年(1968-),男,教授、博士生导师,主研方向为智能信息处理;朱斌,硕士研究生;于文新,讲师、博士;王皖、胡钒梁,硕士研究生。
基金资助:
国家自然科学基金（61973109）。

Side Channel Analysis Attack Based on Deep Learning LSTM

WANG Junnian^1,3, ZHU Bin^1,3, YU Wenxin^2,3, WANG Wan^1,3, HU Fanliang^1,3

1. School of Physics and Electronic Science, Hunan University of Science and Technology, Xiangtan, Hunan 411201, China;
2. School of Information and Electrical Engineering, Hunan University of Science and Technology, Xiangtan, Hunan 411201, China;
3. Key Laboratory of Knowledge Processing and Networked Manufacturing, College of Hunan Province, Xiangtan, Hunan 411201, China

Received:2020-08-10 Revised:2020-10-21 Published:2020-11-05

摘要/Abstract

摘要： 加密数据的安全性受到加密算法和加密设备的影响，为评估密码硬件的可靠性，能量分析等多种针对加密平台的攻击方法得到广泛应用。深度学习是一种性能良好的数据分析方法，基于深度学习的功耗侧信道攻击方法一经提出便引起关注。提出一种基于深度学习LSTM的侧信道攻击方法，利用相关功耗分析方法确定侧信道功耗数据的兴趣点，通过兴趣点位置选择合适的兴趣区间作为特征向量以搭建神经网络模型。实验结果表明，相比MLP和CNN模型，LSTM网络模型在侧信道攻击中具有较高的攻击效率。

关键词: 能量分析, 侧信道攻击, 深度学习, 相关功耗分析, 长短时记忆网络

Abstract: The security of encrypted data is affected by encryption algorithms and encryption devices.The reliability of the encryption devices can be tested by using multiple types of attacks, such as energy analysis.Among different attack methods, the method of side channel attacks based on deep learning has been widely concerned since it was proposed. This paper proposes a side channel attack method based on a deep learning network, LSTM.The method employs Correlation Power Analysis(CPA) to determine the interest points of the side channel power consumption data.Then based on the position of the interest points, an appropriate interest interval is selected as the feature vector to build the neural network model.The experimental results show that the LSTM model has higher efficiency in implementing side channel attacks than MLP and CNN.

Key words: power analysis, side channel attack, deep learning, Correlation Power Analysis(CPA), Long Short-Term Memory(LSTM) network

中图分类号:

TP391

王俊年, 朱斌, 于文新, 王皖, 胡钒梁. 基于深度学习LSTM的侧信道分析[J]. 计算机工程, 2021, 47(10): 140-146.

WANG Junnian, ZHU Bin, YU Wenxin, WANG Wan, HU Fanliang. Side Channel Analysis Attack Based on Deep Learning LSTM[J]. Computer Engineering, 2021, 47(10): 140-146.

http://www.ecice06.com/CN/Y2021/V47/I10/140

图/表 13

20211016173539

20211016173543

20211016173546

20211016173550

20211016173554

20211016173558

20211016173602

20211016173606

20211016173610

20211016173613

20211016173618

20211016173622

20211016173625

参考文献

[1] KOCHER P, JAFFE J, JUN B.Differential power analysis[C]//Proceedings of Annual International Cryptology Conference.Berlin, Germany:Springer, 1999:388-397.
[2] QUISQUATER J J, SAMYDE D.Electromagnetic analysis (ema):measures and counter-measures for smart cards[C]//Proceedings of International Conference on Research in Smart Cards.Berlin, Germany:Springer, 2001:200-210.
[3] KOCHER P C.Timing attacks on implementations of Diffie-Hellman, RSA, DSS, and other systems[C]//Proceedings of Annual International Cryptology Conference.Berlin, Germany:Springer, 1996:104-113.
[4] GOODFELLOW I, BENGIO Y, COURVILLE A, et al.Deep learning[M].Cambridge, USA:MIT Press, 2016.
[5] BACKES M, DÜRMUTH M, GERLING S, et al.Acoustic side-channel attacks on printers[EB/OL].[2020-07-05].https://www.usenix.net/legacy/events/sec10/tech/full_papers/Backes.pdf.
[6] HOSPODAR G, GIERLICHS B, DE MULDER E, et al.Machine learning in side-channel analysis:a first study[J].Journal of Cryptographic Engineering, 2011, 1(4):293-302.
[7] LERMAN L, BONTEMPI G, MARKOWITCH O.Side channel attack:an approach based on machine learning[J].Center for Advanced Security Research Darmstadt, 2011, 5:29-41.
[8] HEUSER A, ZOHNER M.Intelligent machine homicide[C]//Proceedings of International Workshop on Constructive Side-Channel Analysis and Secure Design.Berlin, Germany:Springer, 2012:249-264.
[9] BARTKEWITZ T, LEMKE-RUST K.Efficient template attacks based on probabilistic multi-class support vector machines[C]//Proceedings of International Conference on Smart Card Research and Advanced Applications.Berlin, Germany:Springer, 2012:263-276.
[10] MARTINASEK Z, ZEMAN V.Innovative method of the power analysis[J].Radioengineering, 2013, 22(2):586-594.
[11] BRIER E, CLAVIER C, OLIVIER F.Correlation power analysis with a leakage model[C]//Proceedings of International Workshop on Cryptographic Hardware and Embedded Systems.Berlin, Germany:Springer, 2004:16-29.
[12] PICEK S, HEUSER A, GUILLEY S.Template attack versus Bayes classifier[J].Journal of Cryptographic Engineering, 2017, 7(4):1-9.
[13] GAOMING D, DI X, XIAOQIN L, et al.Identify random delays from side channel traces with HMM[C]//Proceedings of 2013 International Conference on Instrumentation, Measurement, Computer, Communication and Control.Washington D.C., USA:IEEE Press, 2013:1093-1096.
[14] KONG Y, SAEEDI E.The investigation of neural networks performance in side-channel attacks[J].Artificial Intelligence Review, 2019, 52(1):607-623.
[15] LIU B, FENG H, YUAN Z, et al.Learning to attack from electromagnetic emanation[C]//Proceedings of 2012 Asia-Pacific Conference on Environmental Electromagnetics (CEEM).Washington D.C., USA:IEEE Press, 2012:202-205.
[16] HOCHREITER S, SCHMIDHUBER J.Long short-term memory[J].Neural Computation, 1997, 9(8):1735-1780.
[17] LECUN Y, BENGIO Y, HINTON G.Deep learning[J].Nature, 2015, 521(7553):436-444.
[18] HOWARD J, RUDER S.Universal language model fine-tuning for text classification[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics.San Diego, USA:Association for Computational Linguistics, 2018:328-339.
[19] 花君, 严珂, 陆慧娟, 等.基于深度学习LSTM的空调故障诊断[J].中国计量大学学报, 2019, 30(2):197-202. HUA J, YAN K, LU H J, et al.Air conditioner fault diagnosis based on deep learning LSTM[J].Journal of China University of Metrology, 2019, 30(2):197-202.(in Chinese)
[20] 胡涛, 佃松宜, 蒋荣华.基于长短时记忆神经网络的硬件木马检测[J].计算机工程, 2020, 46(7):110-115. HU T, DIAN S Y, JIANG R H.Hardware trojan detection based on long short-term memory neural network[J].Computer Engineering, 2020, 46(7):110-115.(in Chinese)
[21] WANG H, BRISFORS M, FORSMARK S, et al.How diversity affects deep-learning side-channel attacks[C]//Proceedings of 2019 IEEE Nordic Circuits and Systems Conference(NORCAS):NORCHIP and International Symposium of System-on-Chip(SoC).Washington D.C., USA:IEEE Press, 2019:1-7.

选择文件类型/文献管理软件名称

选择包含的内容

基于深度学习LSTM的侧信道分析

Side Channel Analysis Attack Based on Deep Learning LSTM

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 13

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	江雨燕, 陶承凤, 李平. 数据增强和自适应自步学习的深度子空间聚类算法[J]. 计算机工程, 2023, 49(8): 96-103, 110.
[2]	李泽水, 冀俊忠, 杨翠翠. 基于边权重信息深度网络嵌入的PPIN功能模块检测[J]. 计算机工程, 2023, 49(8): 69-76.
[3]	王可铮, 徐玉芬, 周尚波. 结合对比感知损失和融合注意力的图像去雾模型[J]. 计算机工程, 2023, 49(8): 207-214.
[4]	刘俊豪, 王美林, 谢兴, 宋烨兴, 许莉花. 基于改进YOLOv5的皮革瑕疵检测算法[J]. 计算机工程, 2023, 49(8): 240-249.
[5]	闫兴亚, 匡娅茜, 白光睿, 李月. 基于深度学习的学生课堂行为识别方法[J]. 计算机工程, 2023, 49(7): 251-258.
[6]	李军侠, 王星驰, 殷梓, 石德硕. 边缘深度挖掘的弱监督显著性目标检测[J]. 计算机工程, 2023, 49(7): 169-178.
[7]	吴珊, 周凤. 基于改进SSD算法的小目标检测[J]. 计算机工程, 2023, 49(7): 179-188.
[8]	席建锐, 唐红梅, 梁春阳, 刘鑫. 基于改进隐函数的点云物体重建[J]. 计算机工程, 2023, 49(7): 214-222.
[9]	齐咏生, 杜晓旭, 朱俊峰, 高胜利, 刘利强. 基于增强型轻量深度网络的牧区牲畜高效检测[J]. 计算机工程, 2023, 49(7): 278-287.
[10]	谌雨章, 黄逸姿, 张钧涵. 基于多速率空洞卷积的多尺度水下小目标检测[J]. 计算机工程, 2023, 49(6): 257-264.
[11]	陈明, 刘蓉, 张晔. 基于多重注意力机制的中文医疗实体识别[J]. 计算机工程, 2023, 49(6): 314-320.
[12]	张博旭, 蒲智, 程曦. 基于提示学习的维吾尔语文本分类研究[J]. 计算机工程, 2023, 49(6): 292-299,313.
[13]	于海洋, 景鹏, 张文涛, 谢赛飞, 滑志华, 宋草原. 基于残差与注意力机制的道路裂缝检测U-Net改进模型[J]. 计算机工程, 2023, 49(6): 265-273.
[14]	王爱玲, 马文臻, 邹自明, 钟佳. 基于领域自适应的卫星工程参数异常检测[J]. 计算机工程, 2023, 49(5): 29-37,47.
[15]	宋羽凯, 谢江. 基于多任务学习的轻量级语音情感识别模型[J]. 计算机工程, 2023, 49(5): 122-128.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于深度学习LSTM的侧信道分析

Side Channel Analysis Attack Based on Deep Learning LSTM

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 13

参考文献

相关文章 15

编辑推荐

Metrics

本文评价