This project is my Master of Engineering thesis project at the University of York. I am developing an e-mail filter that uses an artificial immune system to determine whether an e-mail is interesting to the user or not. A later extension will be that the filter will be capable of categorising e-mail in user-defined categories.
The advantages to using an artificial immune system are that it is robust, can track trends and respond quickly to changes. Part of my project is to compare its performance to a naive Bayesian mail filter to see if this is a viable approach.
I am using the Spamato spam filter framework (http://www.spamato.net) to produce a plugin that can be used in Mozilla Thunderbird or in Microsoft Outlook.
This project is still in the development phase; a first alpha release is planned for May 2007. Any help in the form of tips and advice is appreciated!
These details are provided for information only. No information here is legal advice and should not be used as such.