期刊文献+

一种基于多层感知机的无监督异常检测方法 被引量:4

Unsupervised anomaly detection based on a multi-layer perceptron
下载PDF
导出
摘要 为了解决入侵检测系统应用过程中需要大量有导师数据进行训练的问题,提出了一种采用多层感知机进行无监督异常检测的方法,网络能够实现编码和还原的功能,从而在最小均方误差原则下学习样本的主要特征,给出了具体的学习算法.依据这些算法构建的系统经过仿真实验取得了较好的结果,验证了基于多层感知机的无监督异常检测方法能够在无需大量有导师信号的情况下检测出入侵,有利于入侵检测系统的推广和应用. A method of unsupervised anomaly detection using a multi-layer perceptron was proposed to solve the problem that a mass of supervised data is needed to apply intrusion detection in computer systems. The network can realize functions of encoding and decoding. The main characteristics of the samples were learned under the principle of least mean square errors. The detailed learning algorithm was discussed. Tests indicate the feasibility of these algorithms. The method of unsupervised anomaly detection based on a multi-layer perceptron can detect intrusions without a mass of supervised data and is fit for application in intrusion detection systems.
作者 关健 刘大昕
出处 《哈尔滨工程大学学报》 EI CAS CSCD 2004年第4期495-498,共4页 Journal of Harbin Engineering University
关键词 异常检测 无监督学习 多层感知机 Decoding Learning algorithms Neural networks Percolation (computer storage)
  • 相关文献

参考文献8

  • 1[1]RICHARD H, GEORGE L, AUTHUR M, et al. The architecture of a network level intrusion detection system [R].New Mexico:New Mexico Department of Computer Science,1990. 被引量:1
  • 2[2]BALASUBRAMANIYAN J S, GARCIA F J O, ISACOFF D,et al. An architecture for intrusion detection using autonomous agents [R].Indiana:Department of Computer Science, Purdue University, 1998. 被引量:1
  • 3[3]DENNING D E. An intrusion detection model [J]. IEEE Transactions on Software Engineering, 1987, 139(2): 222-232. 被引量:1
  • 4[4]YE N, EMRAN S M, CHEN Q,et al. Multivariate statistical analysis of audit trails for host-based intrusion detection [J]. IEEE Transactions on Computers, 2002, 51(7): 810-820. 被引量:1
  • 5[5]JOU Y F, GONG F, SARGOR C,et al. Design and implementation of a scalable intrusion detection system for the protection of network infrastructure [C].Oakland CA:IEEE Computer Society Press,2000 被引量:1
  • 6[6]LANE T, CARLA E B. An empirical study of two approaches to sequence learning for anomaly detection [J]. Machine Learning, 2003, 51(1): 73-107. 被引量:1
  • 7[7]BONIFACIO J M, CANSIAN A M, CARVALHO A C,et al.Neural networks applied in intrusion detection systems [C].Oakland CA:IEEE Computer Society Press,1998. 被引量:1
  • 8[8]ROBERT H N. Replicator neural networks for universal optimal source coding [J]. Science, 1995, 269(9):1 860-1 863. 被引量:1

同被引文献32

引证文献4

二级引证文献11

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