Crosbie and Spafford did work with this approach back in 1995. When used for IDSs, genetic algorithms work by means of a rough set theory where the resulting dataset is used as the inputs for the neural network. I would suggest that you review some of work that has been done in this area to help you with your development. A few links are provided here:
Dig deeper on Network Security Monitoring and Analysis
Related Q&A from Michael Gregg
Enterprise security expert, Michael Gregg answers a question regarding port 3389 issues when a user tries to open port 3389 RDP on their router to ...continue reading
Security expert Michael Gregg notes the risks to enteprise security that mobile devices may cause.continue reading
Expert Michael Gregg answers a reader question about Snort and the interfaces it uses.continue reading
Have a question for an expert?
Please add a title for your question
Get answers from a TechTarget expert on whatever's puzzling you.