文章基本信息

标题：A Combined Naïve Bayes and URL Analysis Based Adaptive Technique for Email Classification
本地全文：下载
作者：Tina R. Patil ; Prof. Dr. V. M. Thakare ; Prof. Dr. S. S. Sherekar 等
期刊名称：International Journal of Electronics, Communication and Soft Computing Science and Engineering
印刷版ISSN：2277-9477
出版年度：2014
卷号：3
期号：Special
出版社：IJECSCSE
摘要：Most content based spam filters are rule based ortrained off-line. Handling new spam tactics is difficult and proneto high misclassification rate. Incremental adaptive spam mailfiltering using Naïve Bayesian classification gives goodperformance, simplicity and adaptability. Phishing emailscontain socially engineered messages to lure victims intoperforming certain actions, such as clicking on a URL whephishing website is hosted, or executing a malware code.model an incremental scheme that receives a stream of emails,and applies the concept of sliding window to train only the last wemails for testing new incoming messages. Subsequently, the nefeatures of tested messages are added to the existing features sothat the model will be adaptive to future incoming emails.study, we extend the approach to the phishing email classificationdomain. The primary motive behind this study is that mphishing email messages contain URLs that point to phishingwebsites, and lexically analyzing the URLs can enhance theclassification accuracy of email messages. Our proposed modelconsists of the combination of the adaptive naïve baysian filterand lexical URL analysis. This model removes oldest emails butkeep the features to train new incoming emails. Lexical URLanalysis is applied on incoming email after preprocessing. Itdetects and classify the host website and reports with ham orspam
关键词：LBS; anonymity; cloaking; location based query;processing.