作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2008, Vol. 34 ›› Issue (12): 160-161. doi: 10.3969/j.issn.1000-3428.2008.12.056

• 安全技术 • 上一篇    下一篇

基于混沌控制系统的神经网络异步加密

邹阿金1,肖秀春1,2   

  1. (1. 广东海洋大学信息学院,湛江 524088;2. 中山大学信息科学与技术学院,广州 510275)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2008-06-20 发布日期:2008-06-20

Asynchronous Encryption of Neural Networks Based on Chaotic Control System

ZOU A-jin1, XIAO Xiu-chun1,2   

  1. (1. Information College, Guangdong Ocean University, Zhanjiang 524088; 2. School of Information Science and Technology, Sun Yat-sen University, Guangzhou 510275)
  • Received:1900-01-01 Revised:1900-01-01 Online:2008-06-20 Published:2008-06-20

摘要: 将Chebyshev神经网络模型作为混沌控制系统辨识器,任选系统初值和非线性、非周期性控制律,通过Chebyshev混沌神经网络产生混沌序列,求出该序列的排序置换及逆置换,对明文置换后即可得密文,密文逆置换即可还原得到明文。理论分析和加密实例表明,该加密算法可异步进行,且只需改变系统初值和控制律,便可获得不同的混沌序列,从而实现“一次一密”加密,具有良好的安全性。

关键词: 神经网络, 混沌, 置换, 异步加密, 控制系统

Abstract: This paper introduces new feed-forward neural networks where hidden units employ orthogonal Chebyshev polynomials for their activation functions and uses it as the identifier of the chaotic control system. Through the Chebyshev neural networks, it can produce chaotic series by varying system initial value and nonlinear, nonperiodic control rule, calculate the sort permutation and inverse permutation of this series, and permute the plaintext to achieve ciphertext, inverse permute the ciphertext to get the plaintext. Theoretical analysis and encryption instances prove that the arithmetic can implement asynchronous one-time pad cipher encryption by varying the system initial value and control rate.

Key words: neural networks, chaos, permutation, asynchronous encryption, control system

中图分类号: