神经网络结构在功耗分析中的性能对比

doi:10.6040/j.issn.1671-9352.3.2018.004

摘要/Abstract

摘要： 为了探究不同的深度神经网络运用在功耗分析攻击中的性能差异,在DPA_Contest_V4数据集的基础上进行实验。破解循环掩码后,首先将深度神经网络与传统的SVM等机器学习算法模型进行对比,然后分析神经网络模型结构的变化对实验结果的影响,最后结合循环神经网络,将不同的网络模型进行综合比较。实验结果表明,在相同实验条件下,神经网络模型要优于传统的机器学习模型,循环神经网络模型要优于深度神经网络模型,其中,不同层数的神经网络采取的激活函数不同,会导致实验结果发生较大变化。

关键词: 深度学习, 神经网络, 功耗分析

Abstract: In order to explore the difference of different neural networks used in power analysis, we use DPA_Contest_V4 dataset to complete our experiment. After the mask is cracked, the deep neural network and the traditional machine learning like SVM are firstly used. Then, the impact of the changes in the structure of the neural network model on the experimental results is analyzed. Finally, a comprehensive comparison of different network models is made by combining the cyclic neural network. The experimental results show that the neural network model is superior to the traditional machine learning model and the recurrent neural network model is superior to the deep neural network model when experimental conditions are the same. Among them, the activation functions of neural networks with different layers are different, which will lead to great changes in the experimental results.

Key words: deep learning, neural network, power analysis

中图分类号:

TP309.2

刘飚,路哲,黄雨薇,焦萌,李泉其,薛瑞. 神经网络结构在功耗分析中的性能对比[J]. 《山东大学学报(理学版)》, 2019, 54(1): 60-66.

LIU Biao, LU Zhe, HUANG Yu-wei, JIAO Meng, LI Quan-qi, XUE Rui. Comparative study on neural network structures in power analysis[J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2019, 54(1): 60-66.

参考文献

[1] LERMAN L, POUSSIER R, BONTEMPI G, et al. Template attacks vs. machine learning revisited(and the curse of dimensionality in side-channel analysis)[C] // Constructive Side-Channel Analysis and Secure Design. Berlin: Springer International Publishing, 2015: 20-33.
[2] GIOMORE R, HANLEY N, et al. Neural network based attack on a masked implementation of AES[C] // IEEE International Symposium on Hardware Oriented Security & Trust. Belfast: IEEE, 2015: 106-111.
[3] MARTINASEK Z, ZAPLETAL O, et al. Power analysis attack based on the MLP in DPA Contest V4[C] // International Conference on Telecommunications & Signal Processing. Kerala: IEEE, 2016: 223-226.
[4] SIMON H. 神经网络与机器学习[M].申富饶,等译.北京:机械工业出版社,2017.
[5] 伊恩·古德费洛,约书亚·本吉奥,亚伦·库维尔. 深度学习[M]. 赵申剑,等译.北京:人民邮电出版社, 2017.
[6] Telecom Paristech Sen Research Group. DPA Contest(4th edition),2013-2014[EB/OL].[2014-5-12].http://www.dpacontest.org/V4/.
[7] NASSAR M,SOUISSI Y, GUILLEY S, et al. RSM: a small and fast countermeasure for AES, secure against 1st and 2nd-order zero-offset SCAs[C] // Design, Automation & Test in Europe Conference and Exposition. Dresden: IEEE Computer Society, 2012: 1173-1178.
[8] RECHBERGER C, OSWALD E. Practical template attacks[J]. Lecture Notes in Computer Science, 2005, 3325(3):440-456.
[9] 邓高明, 张鹏, 赵强,等. 基于PCA和SVM的电磁模板分析攻击[J]. 计算机测量与控制, 2009, 17(9):1837-1839.
[10] ZENG Z, GU D, LIU J, et al. An improved side-channel attack based on support vector machine[C] // Tenth International Conference on Computational Intelligence and Security. Liverpool: IEEE, 2014: 676-680.

相关文章 15

[1]	肖炜茗,王贵君. 基于Bernstein多项式的SISO三层前向神经网络的设计与逼近[J]. 山东大学学报（理学版）, 2018, 53(9): 55-61.
[2]	庞博,刘远超. 融合pointwise及深度学习方法的篇章排序[J]. 山东大学学报（理学版）, 2018, 53(3): 30-35.
[3]	张芳芳,曹兴超. 基于字面和语义相关性匹配的智能篇章排序[J]. 山东大学学报（理学版）, 2018, 53(3): 46-53.
[4]	刘明明,张敏情,刘佳,高培贤. 一种基于浅层卷积神经网络的隐写分析方法[J]. 山东大学学报（理学版）, 2018, 53(3): 63-70.
[5]	李翠平,高兴宝. 求解具有约束的l₁-范数问题的神经网络模型[J]. 《山东大学学报(理学版)》, 2018, 53(12): 90-98.
[6]	秦静,林鸿飞,徐博. 基于示例语义的音乐检索模型[J]. 山东大学学报（理学版）, 2017, 52(6): 40-48.
[7]	王长弘,王林山. 基于忆阻器的S-分布时滞随机神经网络的均方指数稳定性[J]. 山东大学学报（理学版）, 2016, 51(5): 130-135.
[8]	甄艳, 王林山. S-分布时滞随机广义细胞神经网络的均方指数稳定性分析[J]. 山东大学学报（理学版）, 2014, 49(12): 60-65.
[9]	杨阳, 刘龙飞, 魏现辉, 林鸿飞. 基于词向量的情感新词发现方法[J]. 山东大学学报（理学版）, 2014, 49(11): 51-58.
[10]	刘铭, 昝红英, 原慧斌. 基于SVM与RNN的文本情感关键句判定与抽取[J]. 山东大学学报（理学版）, 2014, 49(11): 68-73.
[11]	堵锡华,史小琴,冯长君,李亮. 基于野韭菜挥发性成分的色谱保留指数神经网络预测[J]. 山东大学学报（理学版）, 2014, 49(1): 50-53.
[12]	马奎森,王林山*. S-分布时滞随机BAM神经网络的指数同步[J]. 山东大学学报（理学版）, 2014, 49(03): 73-78.
[13]	常青, 周立群*. 一类具时滞细胞神经网络的全局一致渐近稳定性[J]. J4, 2012, 47(8): 42-49.
[14]	冯新营1,2,计华1,2,张化祥1,2. 基于聚类优化的RBF神经网络多标记学习算法[J]. J4, 2012, 47(5): 63-67.
[15]	段晨霞1,孙刚2,王贵君1*. 正则模糊神经网络对保极大值函数类的泛逼近性[J]. J4, 2012, 47(3): 81-86.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed