Intrusion Detection System Using Visualization And Integration Technique

Intrusion detection is an area of ever increasing importance. Currently existing IntrusionrnDetection Systems (IDS) lack visualization and false alarms detection capabilities.rnResearchers have proposed integrated systems which may reduce the percentage of falsernalarms. This work addresses the above stated problems by integrating Self-Organized Maprn(SOM) with Genetic Algorithm (GA) so as to minimize the false alarms and also to providernvisualization capability to the new IDS. SOM is an unsupervised Artificial Neural Networkrn(ANN) learning algorithm that attempts to visualize a large dataset in compact representation.rnGA is an evolutionary computing type of artificial intelligence algorithm, which is better forrnoptimization, feature selection and clustering problems. The performance of the model isrnmeasured using Knowledge Discovery and Data Mining (KDD) Cup 99 dataset, which wasrnprepared for The Third International Knowledge Discovery and Data Mining (DM) ToolsrnCompetition for researchers who work on intrusion detection. The work also includes GArnbased feature selection to further improve the performance of the model. The result showsrn94.3 % of intrusion detection rate with 2.93% of false alarm rate.

Get Full Work

Report copyright infringement or plagiarism