Design and Implementation of an Optimization System of Spam Filter Rule Based On Neural Network

摘要：

One of the drawbacks of content-based filtering technology is that the system cannot adapt the filter to identify emerging spam characteristics. This paper describes the design and implementation of a spam filtering rules optimization system by introducing BP neural network. It can automatically extract features from incoming emails and learn so as to modify the filtering rules to accommodate new changes. We compare the performance of our system with SpamAssassin.Our experiment results show that the accuracy rate reaches 98.65％.

作者: Ce Zhan Fengli Zhang Mei Zheng

作者单位: School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu, 610054, China

会议类型: 国际会议

会议名称: 2007年通信、电路与系统国际会议(2007 International Conference on Communications,Circuits and Systems Proceedings)

会议地点: 日本福冈

会议语种:英文

在线出版日期: 2007-07-11（万方平台首次上网日期，不代表论文的发表时间）