基于树形奇偶机的神经网络同步新学习规则

doi:10.3724/SP.J.1087.2013.00146

计算机应用 ›› 2013, Vol. 33 ›› Issue (01): 146-148.DOI: 10.3724/SP.J.1087.2013.00146

基于树形奇偶机的神经网络同步新学习规则

梁一峰,廖晓峰,任晓霞

重庆大学计算机学院，重庆 400044

收稿日期:2012-07-29 修回日期:2012-09-10 出版日期:2013-01-01 发布日期:2013-01-09
通讯作者: 梁一峰
作者简介:梁一峰(1987-)，男，黑龙江绥化人，硕士研究生，主要研究方向：信息安全、人工神经网络；廖晓峰(1964-)，男，重庆人，教授，博士，主要研究方向：信息安全、非线性控制理论；任晓霞(1986-)，女，山东德州人，硕士研究生，主要研究方向：CNN图像处理、稳定性理论。
基金资助:
国家自然科学基金资助项目(61163009);重庆市自然科学基金重点资助项目(CSTC2009BA2024)

New neural synchronization learning rule based on tree parity machine

LIANG Yifeng,LIAO Xiaofeng,REN Xiaoxia

College of Computer Science, Chongqing University, Chongqing 400044, China

Received:2012-07-29 Revised:2012-09-10 Online:2013-01-01 Published:2013-01-09
Contact: LIANG Yifeng

摘要/Abstract

摘要： 针对神经密码同步速度慢的问题，基于树形奇偶机(TPM)，提出修改权值的新规则，在同步过程中设置队列用来记录每次通信的结果，实时估计两个互相通信的树形奇偶机的同步程度，并根据估计的结果决定权值修改幅度，在同步程度较低时适当增大权值修改量，在同步程度较高时适当减小权值修改量。仿真实验结果表明，应用新学习规则后同步效率提高了80%以上，同时与几种经典学习规则相比，计算开销更小，安全性得到进一步提高。

关键词: 树形奇偶机, 神经网络, 同步, 神经密码

Abstract: To solve the low speed of synchronization, a new learning rule was proposed by employing Tree Parity Machine (TPM). By setting queues to record the results of each communication in the synchronization process, this rule estimated the degree of synchronization of the two TPMs communicating with each other in real time. According to the results of estimation, the rule selected appropriate values to modify the weights, appropriately increased weight modifications in the lower degree of synchronization and reduced weight modifications in the higher degree of synchronization. Finally, the simulation results show that synchronization efficiency is improved more than 80% by applying new learning rule. Meanwhile, it is also indicated that the rule is computationally inexpensive and it improves the security of communication compared to the classic learning rules.

Key words: Tree Parity Machine (TPM), neural network, synchronization, neural cryptography

中图分类号:

TP309.7

梁一峰廖晓峰任晓霞. 基于树形奇偶机的神经网络同步新学习规则[J]. 计算机应用, 2013, 33(01): 146-148.

LIANG Yifeng LIAO Xiaofeng REN Xiaoxia. New neural synchronization learning rule based on tree parity machine[J]. Journal of Computer Applications, 2013, 33(01): 146-148.

参考文献

［1］METZLER R, KINZEL W, KANTER I. Interacting neural networks ［J］. Physics Review E, 2000, 62(2): 2555-2565.

［2］KINZEL W, METZLER R, KANTER I. Dynamics of interacting neural networks ［J］. Journal of Physics A: Mathematical and General, 2000, 33(14): L141-L147.

［3］KINZEL W, KANTER I. Interacting neural networks and cryptography ［M］// KRAMER B. Advances in Solid State Physics. Berlin: Springer, 2002, 42: 381-391.

［4］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): L707-L713.

［5］RUTTOR A, KINZEL W, SHACHAM L, et al. Neural cryptography with feedback ［J］. Physics Review E, 2004, 69(4): 046110.

［6］RUTTOR A, KINZEL W, KANTER I. Neural cryptography with queries ［J］. Journal Statistical Mechanics: Theory and Experiment, 2005, 2005(1): 01009.

［7］田勇,向涛.神经网路同步的判定及在神经密码中的应用［J］.计算机工程与应用,2011,47(36):109-111.

［8］KANTER I, KINZEL W, KANTER E. 〖HJ1.7mm〗Secure exchange of information by synchronization of neural networks ［J］. Europhysics Letters, 2002, 57(1): 141-147.

［9］KLIMOV A, MITYAGUINE A, SHAMIR A. Analysis of neural cryptography ［C］// ASIACRYPT'02: Proceedings of the 8th International Conference on the Theory and Application of Cryptology and Information Security: Advances in Cryptology. Berlin: Springer, 2003: 823-828.

［10］SHACHAM L N, KLEIN E, MISLOVATY R, et al. Cooperating attackers in neural cryptography ［J］. Physics Review E, 2004, 69(6): 066137.

［11］RUTTOR A, KINZEL W, NAEH T, et al. Genetic attack on neural cryptography ［J］. Physics Review E, 2006, 73(3): 036121.

［12］MISLOVATY R, PERCHENOK Y, KANTER I, et al. Secure key-exchange protocol with an absence of injective functions ［J］. Physics Review E, 2002, 66(6): 066102.

［13］BORNHOLDT S, SCHUSTER H G. Handbook of graphs and networks: from the genome to the Internet ［M］. Weinheim: Wiley-VCH, 2005: 199-216.

［14］KINZEL W, KANTER I. Neural cryptography ［C］// Proceedings of the Ninth International Conference on Neural Information Processing. Washington, DC: IEEE Computer Society, 2002: 1351-1354.

［15］ENGEL A, van den BROECK C. Statistical mechanics of learning ［M］. London: Cambridge University Press, 2001: 14-32.

[1]	廖佳, 陈扬, 包秋兰, 廖雪花, 朱洲森. 计算密集型大流量数据的接力计算与动态分流处理[J]. 计算机应用, 2021, 41(9): 2646-2651.
[2]	刘子辰, 李小娟, 韦伟. 基于循环神经网络的专利价格自动评估[J]. 计算机应用, 2021, 41(9): 2532-2538.
[3]	王贺兵, 张春梅. 基于非对称卷积-压缩激发-次代残差网络的人脸关键点检测[J]. 计算机应用, 2021, 41(9): 2741-2747.
[4]	宋中山, 梁家锐, 郑禄, 刘振宇, 帖军. 基于双向门控尺度特征融合的遥感场景分类[J]. 计算机应用, 2021, 41(9): 2726-2735.
[5]	李康康, 张静. 基于注意力机制的多层次编码和解码的图像描述模型[J]. 计算机应用, 2021, 41(9): 2504-2509.
[6]	张永斌, 常文欣, 孙连山, 张航. 基于字典的域名生成算法生成域名的检测方法[J]. 计算机应用, 2021, 41(9): 2609-2614.
[7]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[8]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[9]	牟长宁, 王海鹏, 周丕宇, 侯鑫行. 基于图卷积神经网络的串联质谱从头测序[J]. 计算机应用, 2021, 41(9): 2773-2779.
[10]	曹玉红, 徐海, 刘荪傲, 王紫霄, 李宏亮. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8): 2273-2287.
[11]	丁尹, 桑楠, 李晓瑜, 吴飞舟. 基于循环神经网络的电信行业容量数据预测方法[J]. 计算机应用, 2021, 41(8): 2373-2378.
[12]	秦斌斌, 彭良康, 卢向明, 钱江波. 司机分心驾驶检测研究进展[J]. 计算机应用, 2021, 41(8): 2330-2337.
[13]	黄程程, 董霄霄, 李钊. 基于二维Winograd算法的深流水线5×5卷积方法[J]. 计算机应用, 2021, 41(8): 2258-2264.
[14]	曾祥银, 郑伯川, 刘丹. 基于深度卷积神经网络和聚类的左右轨道线检测[J]. 计算机应用, 2021, 41(8): 2324-2329.
[15]	武光利, 李雷霆, 郭振洲, 王成祥. 基于改进的双向长短期记忆网络的视频摘要生成模型[J]. 计算机应用, 2021, 41(7): 1908-1914.

基于树形奇偶机的神经网络同步新学习规则

New neural synchronization learning rule based on tree parity machine

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics