| 基于网络会话层的垃圾邮件行为识别 |
| |
| 引用本文： | 白秋颖,章璿,张耀龙. 基于网络会话层的垃圾邮件行为识别[J]. 计算机工程与应用, 2007, 43(1): 167-169 |
| |
| 作者姓名： | 白秋颖 章璿 张耀龙 |
| |
| 作者单位： | 鞍山科技大学,计算机科学与工程学院,辽宁,鞍山,114044;北京邮电大学,智能科学技术研究中心,北京,100876 |
| |
| 基金项目： | 国家高技术研究发展计划(863计划) |
| |
| 摘 要： | 目前最流行的邮件内容过滤技术工作在网络应用层,通过对邮件内容的分析来判别邮件的合法性,无法避免由于垃圾邮件的泛滥而造成的网络带宽资源的浪费。针对这种情况,论文提出一种基于网络会话层的垃圾邮件行为识别方法。该方法运用决策树算法,对邮件发送过程中的网络会话层数据进行挖掘,发现垃圾邮件的行为规律,在垃圾邮件的内容数据发送前就对其实施过滤,有效地解决了垃圾邮件占用网络带宽的问题,是对当前各种垃圾邮件过滤技术的一个有益的补充。
|
| 关 键 词： | 邮件过滤 行为识别 数据挖掘 决策树 |
| 文章编号： | 1002-8331（2007）01-0167-03 |
| 修稿时间： | 2006-05-01 |
Spam behavior recognition based on data mining in session layer |
| |
| BAI Qiu-ying,ZHANG Xuan,ZHANG Yao-long. Spam behavior recognition based on data mining in session layer[J]. Computer Engineering and Applications, 2007, 43(1): 167-169 |
| |
| Authors: | BAI Qiu-ying ZHANG Xuan ZHANG Yao-long |
| |
| Affiliation: | 1.School of Computer Science and Engineefing,Anshan University of Science and Technology,Anshan,Liaoning 114044,China; 2.CISTR,Beijing University of Posts and Telecommunications,Beijing 100876,China |
| |
| Abstract: | The most popular mail content filtering technology at present works on the application layer of network,which judges the legitimacy of the mail by analyzing the content of the mail.It can't avoid wasting the network bandwidth because of the overflowing spam.To deal with the problem,the paper proposes a method of spam behavior recognition based on data mining in session layer.The method applies decision tree algorithm to data in network session layer,finds the rule of the spam behavior,and filters the spam before the content data of the spam have been sent.This method solves unwanted spam traffic effectively,and it is a beneficial supplement of the current various spam filter technologies. |
| |
| Keywords: | spam filtering behavior recognition data mining decision tree |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
