基于DTMP和快速学习规则的神经密码算法

doi:10.11772/j.issn.1001-9081.2015.06.1683

计算机应用 ›› 2015, Vol. 35 ›› Issue (6): 1683-1687.DOI: 10.11772/j.issn.1001-9081.2015.06.1683

基于DTMP和快速学习规则的神经密码算法

张力生¹, 刘凤钗¹, 董滔², 张化川¹, 胡文婕³

1. 重庆邮电大学软件工程研究中心, 重庆 400065;
2. 西南大学电子信息工程学院, 重庆 400715;
3. 重庆邮电大学经济管理学院, 重庆 400065

收稿日期:2015-01-13 修回日期:2015-03-26 发布日期:2015-06-12
通讯作者: 张化川(1979-),男,四川大竹人,讲师,硕士,CCF会员,主要研究方向:数据挖掘、神经网络;zhanghc@cqupt.edu.cn
作者简介:张力生(1965-),男,四川宜宾人,教授,硕士,CCF会员,主要研究方向:数据挖掘、神经网络;刘凤钗(1988-),女,河北石家庄人,硕士研究生,主要研究方向:神经密码学;董滔(1981-),男,重庆人,副教授,博士,主要研究方向:神经网络;胡文婕(1981-),女,重庆人,讲师,博士,主要研究方向:复杂网络。
基金资助:
重庆市自然科学基金资助项目(ctsc2014cyjA40053);重庆市教委科学技术研究项目(KJ130519)。

Neural cryptography algorithm based on "Do not Trust My Partner" and fast learning rule

ZHANG Lisheng¹, LIU Fengchai¹, DONG Tao², ZHANG Huachuan¹, HU Wenjie³

1. Research Center for Software Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China;
2. College of Electronic and Information Engineering, Southwest University, Chongqing 400715, China;
3. School of Economics and Management, Chongqing University of Posts and Telecommunications, Chongqing 400065, China

Received:2015-01-13 Revised:2015-03-26 Published:2015-06-12

摘要/Abstract

摘要：

针对神经密码中如何以较短的同步时间获得较高的安全性这一密钥交换问题,提出了一种基于"不要相信我的伙伴"(DTMP)和快速学习规则的联合算法。该算法可以通过在公共信道上以一定的概率发送错误比特来干扰攻击者对交互信息的窃听,以达到降低被动攻击成功率的目的,同时通过估计通信双方神经网络输出不相等的概率来判断通信双方的同步程度;然后根据通信双方的同步程度来确定权值的修改幅度,从而加快同步进程。仿真实验表明,联合算法所需同步时间比原DTMP算法少,且当通信双方不同时发送错误信息时,联合算法的安全性略高于DTMP原算法;而与反馈算法相比,联合算法在同步时间和安全性方面优势明显。实验结果表明联合算法能以较短的同步时间获得较高的安全性。

关键词: 树型奇偶机, 不要相信我的伙伴, 学习规则, 几何攻击, 简单攻击

Abstract:

Focusing on the key exchange problem of how to get the higher security for neural cryptography in the short time of the synchronization, a new hybrid algorithm combining the features of "Do not Trust My Partner" (DTMP) and the fast learning rule was proposed. The algorithm could send erroneous output bits in the public channel to disrupt the attacker's eavesdropping of the exchanged bits and reduce the success rate of passive attack. Meanwhile, the proposed algorithm estimated the synchronization by estimating the probability of unequal outputs, then adjusted the change of weights according to the level of synchronization to speed up the process of synchronization. The simulation results show that the proposed algorithm outperforms the original DTMP in the time needed for the partners to synchronize. Moreover, the proposed algorithm is securer than the original DTMP when the partners do not send erroneous output bits at the same time. And the proposed algorithm outperforms the feedback algorithm in both the synchronization time and security obviously. The experimental results show that the proposed algorithm can obtain the key with a high level of security and a less synchronization time.

Key words: Tree Parity Machine (TPM), Do not Trust My Partner (DTMP), learning rule, geometric attack, simple attack

中图分类号:

TP309.7

张力生, 刘凤钗, 董滔, 张化川, 胡文婕. 基于DTMP和快速学习规则的神经密码算法[J]. 计算机应用, 2015, 35(6): 1683-1687.

ZHANG Lisheng, LIU Fengchai, DONG Tao, ZHANG Huachuan, HU Wenjie. Neural cryptography algorithm based on "Do not Trust My Partner" and fast learning rule[J]. Journal of Computer Applications, 2015, 35(6): 1683-1687.

参考文献

[1] DIFFIE W, HELLMAN M E. New directions in cryptography [J]. IEEE Transactions on Information Theory, 1976, 22(6): 644-654.
[2] ROSEN-ZVI M, KANTER I, KINZEL W. Cryptography based on neural networks-analytical results [J]. Journal of Physics A: Mathematical and General, 2002, 35(47): 707-713.
[3] ROSEN-ZVI M, KLEIN E, KANTER I, et al. Mutual learning in a tree parity machine and its application to cryptography [J]. Physical Review E, 2002, 66(6): 135-138.
[4] VOLKMER M, WALLNER S. Tree parity machine rekeying architectures [J]. IEEE Transactions on Computers, 2005, 54(4): 421-427.
[5] CAI J, LIU D, CHEN T. Review of neural cryptography [J]. Journal of Computer Applications, 2007, 27(S1): 219-222.(蔡家楣, 刘多, 陈铁铭.神经网络密码学研究综述[J].计算机应用, 2007, 27(S1):219-222.)
[6] RUTTOR A, KINZEL W, NAEH R, et al. Genetic attack on neural cryptography [J]. Physical Review E, 2006, 73(3): 132-136.
[7] SHACHAM L N, KLEIN E, MISLOVATY R, et al.Cooperating attackers in neural cryptography [J]. Physics Review E, 2004, 69(6): 5-11.
[8] MISLOVATY R, PERCHENOK Y, KANTER I, et al. Secure key-exchange protocol with an absence of injective functions [J]. Physical Review E, 2002, 66(6): 102-108.
[9] RUTTOR A, KINZEL W, KANTER I. Dynamics of neural cryptography [J]. Physical Review E, 2007, 75(5): 56-58.
[10] RUTTOR A, KINZEL W, SHACHAM L, et al. Neural cryptography with feedback [J]. Physical Review E, 2004, 69(4): 7-9.
[11] ALLAM A M, ABBAS H M. On the improvement of neural cryptography using erroneous transmitted information with error prediction [J]. IEEE Transactions on Neural Networks, 2010, 21(12): 1915-1924.
[12] LIANG Y, LIAO X, REN X. New neural synchronization learning rule based on tree parity machine [J]. Journal of Computer Applications, 2013, 33(1): 146-148. (梁一峰, 廖晓峰, 任晓霞.基于树型奇偶机的神经网络同步新学习规则[J].计算机应用, 2013, 33 (1):146-148.)
[13] ZHANG L, YAN W, LUO C. New learning rule of neural cryptography based on queue mechanism [J]. Application Research of Computers, 2014, 31(10): 3095-3099. (张力生, 严威, 罗成娥.一种基于队列机制的神经密码学的新学习规则[J].计算机应用研究, 2014, 31 (10): 3095-3099.)

基于DTMP和快速学习规则的神经密码算法

Neural cryptography algorithm based on "Do not Trust My Partner" and fast learning rule

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 10

编辑推荐

Metrics

[1]	陈淑琴, 李智, 程欣宇, 高奇. 人眼视觉特性与SIFT相结合的视频双水印算法[J]. 计算机应用, 2017, 37(7): 1936-1942.
[2]	程兴宏侯榆青程璟星蒲鑫. 基于图像Tchebichef矩抗几何攻击的零水印算法[J]. 计算机应用, 2013, 33(02): 434-437.
[3]	曲巨宝林宏基. 基于特征点密度的DCT域盲检测数字水印算法[J]. 计算机应用, 2011, 31(10): 2670-2673.
[4]	崔得龙左敬龙彭志平. 基于范重心抗局部非线性几何攻击水印算法[J]. 计算机应用, 2010, 30(8): 2161-2163.
[5]	苗锡奎孙劲光张语涵. 分形与伪Zernike矩的鲁棒水印算法研究[J]. 计算机应用, 2010, 30(4): 1038-1041.
[6]	刘晶王映辉何文娟. 基于图像特征点的数字水印算法[J]. 计算机应用, 2010, 30(3): 702-704.
[7]	肖迎杰孙劲光张云. 一种模板和图像特征相结合的数字水印算法[J]. 计算机应用, 2010, 30(1): 50-53.
[8]	马晓普刘妍. 基于统计特征的鲁棒图像拷贝检测技术[J]. 计算机应用, 2009, 29(08): 2233-2235.
[9]	张杰勇刘守义尹忠海. 一种抗几何攻击盲数字水印方法[J]. 计算机应用, 2008, 28(9): 2249-2251.
[10]	杨梅娟陈亚军 . 变共轭梯度算法及其在农产品总产量预测中的应用[J]. 计算机应用, 2006, 26(11): 2765-2768.