Detection of Spain e-mails by analyzing the distributing behaviors of e-mail servers

Authors:
Ling-Sheng Tseng;Chih-Hung Wu
Affiliations:
Department of Information Management, Shu-Te University, Taiwan, R.O.C.;Department of Information Management, Shu-Te University, Taiwan, R.O.C.
Venue:
Design and application of hybrid intelligent systems
Year:
2003

Citing 6
Cited 1

Support-Vector Networks

Machine Learning
Representation of electronic mail filtering profiles: a user study

Proceedings of the 5th international conference on Intelligent user interfaces
An experimental comparison of naive Bayesian and keyword-based anti-spam filtering with personal e-mail messages

SIGIR '00 Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval
Mining e-mail content for author identification forensics

ACM SIGMOD Record
Challenges of the Email Domain for Text Classification

ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Support vector machines for spam categorization

IEEE Transactions on Neural Networks

Behavior-based spam detection using a hybrid method of rule-based techniques and neural networks

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

The spam problem is a serious side-effect of the abuse of e-mails, which is getting worse every day. Spams can be traced by keyword-identification on the message bodies. However, by observing the distributing behaviors of e-mails, we found that it also can be identified by analyzing the delivering patterns on mail servers. In this research, we analyze the behaviors of users in sending/receiving e-mails and try to detect spam e-mails by monitoring if such patterns do happen on mail servers. Such behavioral patterns are summarized and categorized into 20 types. We have developed a knowledge-based system that monitors the behaviors of e-mail servers for early alert of being spammed. Experimental results show that our method is workable and effective and can successfully identify spams.