Machine Learning
Representation of electronic mail filtering profiles: a user study
Proceedings of the 5th international conference on Intelligent user interfaces
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
Hi-index | 0.00 |
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.