反垃圾电子邮件方法研究进展  

Advances in anti-spam techniques

作　　者：谭营[1,2] 朱元春[1,2] 

机构地区：[1]北京大学机器感知与智能教育部重点实验室,北京100871 [2]北京大学信息科学技术学院,北京100871

出　　处：《智能系统学报》2010年第3期189-201,共13页CAAI Transactions on Intelligent Systems

基　　金：国家"863"计划资助项目(2007AA01Z453);国家自然科学基金资助项目(60673020;60875080)

摘　　要：随着垃圾电子邮件对互联网技术的威胁日益严峻,反垃圾电子邮件研究已成为当今的研究热点.综述了反垃圾电子邮件研究的历史、现状和最新进展.首先介绍并分析了3种类型的邮件特征提取方法——基于文本、图片和行为的特征提取方法.然后,在此基础上,详细论述了当前的反垃圾邮件技术——法律手段、简单方法和智能型处理技术.接着,介绍了反垃圾邮件系统性能评估准则和标准数据集.最后,对反垃圾电子邮件现状进行了分析和总结,并指明了未来反垃圾电子邮件研究的发展方向,包括改进邮件特征提取技术、完善相关法案和引入新的智能反垃圾邮件方法.As the threat of spam on the Internet grows increasingly severe,anti-spam techniques have become a hotspot for researchers.The authors reviewed the history,current situation,and latest advances in research on spam control.First,we introduced and analyzed three different types of feature extraction methods for email.These were text-based,image-based,and behavior-based approaches.Then,current anti-spam techniques were described and discussed.These included laws,simple methods,and intelligent approaches.After that,performance evalua-tion methods and standard data sets were discussed.Finally,we summarized the current research on anti-spam techniques and pointed out directions for future research,including improvements to e-mail feature extraction tech-niques,improvements to laws,and new intelligent anti-spam approaches.

关 键 词：反垃圾电子邮件 特征提取 智能检测技术 性能评估 

分 类 号：TP393.098[自动化与计算机技术—计算机应用技术]