期刊文献+

基于Levenberg-Marquardt算法的用户击键特征鉴别 被引量:7

Keystroke Characteristics Identity Authentication Based on Levenberg-Marquardt Algorithm
下载PDF
导出
摘要 Levenberg Marquardt算法是神经网络、高斯 牛顿法与梯度下降法的结合 ,既有神经网络的自学习特性 ,也有高斯 牛顿法的快速收敛特性 ,还有梯度下降法的全局搜索特性。文中将Levenberg Marquardt算法应用于对用户输入口令时敲击键盘的时间特征进行分析鉴别 ,从而进行用户附加身份认证。研究表明 ,LM算法显示出速度快、识别准确率高的优越性能。 Levenberg Marquardt (LM) algorithm is a combination of neural network, Gauss Newton method and gradient descent method, so it has the abilities of self learning, fast convergence and global search. In this paper LM algorithm is employed to abstract the users keystroke characteristics captured when passwords are typed, and, as a result, to authenticate the identity of the users. It is shown in this paper that LM algorithm has the advantages of fast recognition and low false rate.
出处 《计算机应用》 CSCD 北大核心 2004年第7期108-109,112,共3页 journal of Computer Applications
关键词 击键动力学 LM算法 高斯-牛顿法 梯度下降法 keystroke dynamics LM algorithm Guass Newton method gradient descent method
  • 相关文献

参考文献6

  • 1Monrose F, Rubin AD. Keystroke dynamics as a biometric for authentication[ J]. Future Generation Computing System, 2000, 16(4): 351 -359.
  • 2Haider S, Abbas A, Zaidi AK. A multi-technique approach for user identification through keystroke dynamics[ A]. Proc of IEEE International Conf on Systems, Man, and Cybernetics[ C], 2000, Vol 2.1336 - 1341.
  • 3Obaidat MS, Macchairolo DT. A multilayer neural network system for computer access security[ J]. IEEE Trans on Systems, Man and Cybernetics, 1994, 24(5): 806 -813.
  • 4Obaidat MS , Sadoun B . Keystroke dynamics based authentication [ A]. Jain A, Bolle R, Pankanti S, ed. Biometrics Personal Identification in Networked Society[ C]. Kluwer Academic Publishers,1998. 213 - 225.
  • 5Lin DT. Computer-access authentication with neural network based keystroke identity verification[ A]. Proc of IEEE International Conf on Neural Networks[ C], 1997, Vol1. 174 - 178.
  • 6Haykin S. Neural networks: a comprehensive foundation[ M]. 2nd Edition. Beijing: Tsinghua University Press, Prentice Hall, 2001.

同被引文献56

引证文献7

二级引证文献18

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部