[1]邹阿金,张雨浓,肖秀春.Hermite混沌神经网络异步加密算法[J].智能系统学报,2009,4(05):458-462.[doi:10.3969/j.issn.1673-4785.2009.05.012]
 ZOU A-jin,ZHANG Yu-nong,XIAO Xiu-chun.An asynchronous encryption algorithm based on Hermite chaotic neural networks[J].CAAI Transactions on Intelligent Systems,2009,4(05):458-462.[doi:10.3969/j.issn.1673-4785.2009.05.012]
点击复制

Hermite混沌神经网络异步加密算法(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第4卷
期数:
2009年05期
页码:
458-462
栏目:
出版日期:
2009-10-25

文章信息/Info

Title:
An asynchronous encryption algorithm based on Hermite chaotic neural networks
文章编号:
1673-4785(2009)05-0458-05
作者:
邹阿金12张雨浓2肖秀春12
1.广东海洋大学信息学院,广东湛江524088; 2. 中山大学信息与技术学院,广东广州510275
Author(s):
ZOU A-jin12 ZHANG Yu-nong1 XIAO Xiu-chun12
1.Information College, Guangdong Ocean University, Zhanjiang 524088, China; 2.School of Information Science and Technology, Sun Yatsen University, Guangzhou 510275, China
关键词:
Hermite神经网络正交多项式混沌异步加密
Keywords:
Hermite neural networks orthogonal polynomial chaos asynchronous encryption
分类号:
TP183;TN918
DOI:
10.3969/j.issn.1673-4785.2009.05.012
文献标志码:
A
摘要:
基于最佳均方逼近,采用Hermite正交多项式做为神经网络隐层的激励函数,引入一种新型的Hermite神经网络模型.通过神经网络权值和混沌初值产生性能接近于理论值的混沌序列,从中提取与明文等长的序列进行排序,将排序结果对明文置换后即可得密文.加密与解密信息完全隐藏于神经网络产生的混沌序列中,与混沌初值无显式关系,且只需改变混沌初值,便可实现“一次一密”异步加密,其安全性取决于混沌序列的复杂性和无法预测性.理论分析和加密实例表明,该加密算法简单易行,克服了混沌同步加密的诸多缺陷,具有良好的安全性.
Abstract:
This paper introduces a new Hermite neural network model, in which orthogonal Hermite polynomials were employed as the activation functions of hidden layers of feed-forward neural networks by using best square approximation theory. By varying the chaotic initial value and regarding it as the input of the networks, new chaotic series were generated, which were close to the theoretical values. From the new chaotic series, a sub-sequence with the same length as the plaintext was extracted and sorted. Then, by replacing the sorted results with the plain-text, cipher-text was produced. In the encryption system, the information needed in encryption and decryption was hidden in the chaotic series and has no obvious relationship with the initial chaotic value. Security depends completely on the complexity and unpredictability of the chaotic sequences. By varying the initial chaotic value, we can implement asynchronous one-time pad cipher encryption. Theoretical analysis and encryption tests proved that our algorithm is useful, simple and highly secure, with many advantages that a synchronous system can never achieve.

参考文献/References:

[1]PECORA L M, CARROLL T L. Synchronization in chaotic system[J]. Physical Review Letters, 1990, 64(8): 821-824.
[2]CROUNSE K R, YANG T, CHUA L O. Pseudo-random sequence generation using the CNN universal machine with applications to cryptography[C]//Proceedings of the IEEE Intemational Workshop on Cellular Neural Networks and Their Applications. Singapore: World Scientific Press, 1996: 433-438.
[3]MILANOVIC V, ZAQHLOUL M E. Synchronization of chaotic neural networks for secure communications[J]. IEEE Intemational Symposium on Circuits and Systems, 1996, 3: 28-31.
[4]GUO D, CHEN L M, CHEN L L. A new symmetric probabilistic encryption scheme based on chaotic attractors of neural networks[J]. Applied Intelligence, 1999, 10: 71-84.
[5]王    喆,陈   玲,朱双鹤. 基于径向基函数神经网络的混沌加密方案[J].空军工程大学学报, 2003, 4(3): 54-57.
 WANG Zhe, CHEN Ling, ZHU Shuanghe. Chaotic encryption based on RBF neural networks[J]. Journal of Air Force Engineering University, 2003, 4(3): 54-57.
[6]齐   锐, 张大力, 阎平凡. 基于神经网络的对称密码系统[J]. 清华大学学报:自然科学版, 2001, 41(9): 89-93.
QI Rui, ZHANG Dali, YAN Pingfan. A symmertic cryptosystem by neural network[J]. Journal of Tsinghua University: Science and Technology, 2001, 41(9): 89-93.
[7]姜    丽, 杨明福, 黄桂敏. 一种基于神经网络的多级混沌加密算法[J]. 计算机应用与软件, 2006, 23(8):106-108.
 JIANG Li, YANG Mingfu, HUANG Guimin. A multistage chaotic encryption algorithm based on neural network[J]. Computer Applications and Software, 2006, 23(8):106-108.
[8]YANG Tao. Chaotic secure communication systems: history and new results[J]. Telecommunication Review, 1999, 9(4): 597-634.
[9]YANG T, WU C W, CHUA L O. Cryptography based on chaosic systems[J]. IEEE Transactions on Circuits and System: Fundamental Teheory and Apphcations, 1997, 44(5): 469-472.
[10]刘年生, 郭东辉, 吴伯僖. 混沌神经网络及其在保密通讯中的应用[J]. 电讯技术, 2002, 5:141-147.
LIU Niansheng, GUO Donghui, WU Boxi. A symmetric block encryption sheme based on chaotic series of neural networks[J]. Telecommunication Engineering, 2002, 5:141-147.
[11]张雨浓, 陈扬文, 易称福, 等. Hermite正交基前向神经网络的权值直接确定法[J]. 甘肃科学学报, 2008, 20(1):82-86.
 ZHANG Yunong, CHEN Yangwen, YI Chengfu, et al. Feedforward neural network activated with Hermite orthogonal polynomials and its weightsdetermination method[J]. Journal of Gansu Sciences, 2008, 20(1): 82-86.
[12]SHANNON C E. Communication theory of secrecy system [J]. Bell Syst Tech J, 1949, 28: 656-715.

备注/Memo

备注/Memo:
作者简介:
邹阿金,男,1963年生,硕士,副教授,中山大学2008年度访问学者.主要研究方向为神经网络、信息安全.参与多项国家自然科学基金项目、煤炭系统留学回国人员科技基金资助项目1项,发表学术论文30余篇,出版专著和编著各1部.

张雨浓,男,1973年生,教授,博士生导师,博士.主要研究方向为神经网络、机器人、高斯过程及其科学计算与优化.先后在香港中文大学、新加坡国立大学、英国Strathclyde大学和爱尔兰国立大学从事神经网络研究,多次参加和参与组织相关学术会议并担任组委会成员和主席等职务.主持国家自然科学基金项目2项、中山大学校项目2项.2007年入选教育部“新世纪优秀人才支持计划”.发表学术论文70余篇,其中被SCI检索18篇、EI检索30余篇,出版专著1部.

肖秀春,男,1976年生,讲师,博士研究生.主要研究方向为计算机图形图像处理、信号检测与智能信息处理,发表学术论文近10篇.
更新日期/Last Update: 2009-12-29