一种新型的基于URL过滤的反垃圾邮件技术  

Research of novel anti-spam technique based on URL filtering

作　　者：吴峻[1] 李洋[2] 

机构地区：[1]湘潭大学,湖南湘潭411100 [2]中国科学院计算技术研究所,北京100080

出　　处：《计算机应用研究》2008年第5期1537-1539,共3页Application Research of Computers

基　　金：国家“973”计划资助项目(2004CB318109)

摘　　要：在深入分析了传统垃圾邮件过滤技术不足的基础上,提出并实现了一种新型的基于URL过滤的垃圾邮件过滤技术(URLbased spamfiltering,UBSF)。该方法通过对比从到来邮件中提取的URL与URL库中存储的URL信息的相似性来判定垃圾邮件。通过语料库以及构建实际系统原型的测试,表明该方法具有准确性高、误报率低以及实时处理速度快的优点。A novel anti-spam technique was proposed and implemented based on URL filtering on the basis of analysed over the traditional anti-spam techniques. The technique determined spam by comparing the similarity of the abstracted URLs from incoming mail and the URLs from the preset URL library. Experimental evaluation from both mail corpus and the constructed prototype based on the novel technique illustrates that the technique has some advantages, such as high accuracy, low false positives and good real-time processing ability.

关 键 词：网络安全 垃圾邮件过滤 URL过滤的垃圾邮件过滤技术 统一资源定位符库 

分 类 号：TP393.08[自动化与计算机技术—计算机应用技术]