HUANG Jie,WANG Yi.Experimental Study on the Structure of Convolutional Neural Network Suitable for Side Channel Analysis[J].Journal of Chengdu University of Information Technology,2019,(05):449-456.[doi:10.16836/j.cnki.jcuit.2019.05.001]
适用于侧信道分析的卷积神经网络结构的实验研究
- Title:
- Experimental Study on the Structure of Convolutional Neural Network Suitable for Side Channel Analysis
- 文章编号:
- 2096-1618(2019)05-0449-08
- 分类号:
- TN911
- 文献标志码:
- A
- 摘要:
- 侧信道分析中,对模板攻击的模板建立研究已经从高斯分布转变到使用机器学习算法来建立模板。比如使用支持向量机、神经网络等。但是使用神经网络进行侧信道分析时,网络结构的设计参数众多,找到合适的网络结构很困难。基于大量的实验研究,总结并提出适用于侧信道分析的卷积神经网络结构的经验,为今后设计侧信道攻击中的卷积神经网络提供依据。
- Abstract:
- In the side channel analysis, the template construct research of template attack has transformed from Gaussian distribution to machine learning algorithm. For example, use support vector machines, neural networks, and so on. However,when using neural networks for side channel analysis, it is difficult to find a suitable network structure due to the large number of design parameters of the network structure. Based on the large number of experimental studies, this paper summarizes and presents the experience of convolutional neural network structure suitable for side channel analysis. It provides a basis for designing the convolutional neural network in the future.
参考文献/References:
[1] 杜之波,吴震,王敏,等.针对SM4轮输出的改进型选择明文功耗分析攻击[J].通信学报,2015,36(10):85-91.
[2] 吴震,王敏,饶金涛,等.针对基于SM3的HMAC的能量分析攻击方法[J].通信学报,2016,37(5):38-43.
[3] 杜之波,吴震,王敏,等.基于SM3的动态令牌的能量分析攻击方法[J].通信学报,2017,38(3):65-72.
[4] Kocher P C.Timing attacks on implementations of Diffie-Hellman,RSA,DSS,and other systems[C].Annual International Cryptology Conference,1996.
[5] Kocher P.Introduction to differential power analysis and related attacks[EB/OL].http://www.cryptography.com/dpa/technical/index.html,1998.
[6] Chari S,Rao J R,Rohatgl P.Template attacks[M].Cryptographic Hardware and Embedded Systems-CHES 2002.ed:Springer,2003.
[7] Picek,S,Heuser,A,Guilley,S.Template attack versus Bayes classifier[J].Journal of Cryptographic Engineering,2017(7):343-351.
[8] Bartkewitz,T Lemke-rust K.Efficient template attacks based on probabilistic multi-class support vector machines[J].Springer,2013:263-276.
[9] Martinasek Z,Hajny J,Malina L.Optimization of power analysis using neural network[C].International Conference on Smart Card Research and Advanced Applications,2013.
[10] Zdenek Martinasek,Petr Dzurenda,Lukas Malina.Profiling power analysisattack based on MLP in DPA contest V4.2[C].In 39th International Conferenceon Telecommunications and Signal Processing.TSP,2016.
[11] Martinasek Z,Hajny J,Malina L.Optimization of power analysis using neural network[C].International Conference on Smart Card Research and Advanced Applications,Springer Cham,2013:94-107.
[12] Zdenek Martinasek,Lukas Malina,K Trasy.Profiling Power Analysis Attack Based on Multi-layer Perceptron Network[J].Computational Problems inScience and Engineering,2015(343):317-339.
[13] Eleonora Cagli,Cecile Dumas,Emmanuel Prouff.Convolutional neural networks with data augmentation against jitter-based countermeasures-profiling attacks without pre-processing[C].In Wieland Fischer and Naofumi Homma,editors,Cryptographic Hardware and Embedded Systems-CHES 2017-19th International Conference,Taipei,Taiwan,2017.
[14] Benadjila R,Prouff E,Strullu R,et al.Study of Deep Learning Techniques for Side-Channel Analysis and Introduction to ASCAD Database[J].ANSSI,France & CEA,LETI,MINATEC Campus,France,2018(53).
相似文献/References:
[1]匡晓云,黄开天,兰 天,等.针对SM4密码算法的模板攻击[J].成都信息工程大学学报,2021,36(05):499.[doi:10.16836/j.cnki.jcuit.2021.05.004]
KUANG Xiaoyun,HUANG Kaitian,LAN Tian,et al.Template Attack Against SM4 Cryptographic Algorithm[J].Journal of Chengdu University of Information Technology,2021,36(05):499.[doi:10.16836/j.cnki.jcuit.2021.05.004]
备注/Memo
收稿日期:2019-03-13基金项目:“十三五”国家密码发展基金资助项目(MMJJ20180244); 国家科技重大专项基金资助项目(2014ZX01032401); 四川省教育厅重点科研基金资助项目(17ZB0082); 四川省重点研发资助项目(2019YFG0096)