eduzhai > Applied Sciences > Computer Science >

Implementation of Network Intrusion Detection System Using Soft Computing Algorithms (Self Organizing Feature Map and Genetic Algorithm)

  • carsar
  • (0) Download
  • 20210407
  • Save

... pages left unread,continue reading

Document pages: 24 pages

Abstract: In today’s world, computer network is evolving very rapidly. Most publicor and private companies set up their own local networks system for thepurpose of promoting communication and data sharing within the companies.Unfortunately, their data and local networks system are under risks.With the advanced computer networks, the unauthorized users attempt toaccess their local networks system so as to compromise the integrity, confidentialityand availability of resources. Multiple methods and approacheshave to be applied to protect their data and local networks system against maliciousattacks. The main aim of our paper is to provide an intrusion detectionsystem based on soft computing algorithms such as Self Organizing FeatureMap Artificial Neural Network and Genetic Algorithm to network intrusiondetection system. KDD Cup 99 and 1998 DARPA dataset were employedfor training and testing the intrusion detection rules. However, GA’s traditionalFitness Function was improved in order to evaluate the efficiency andeffectiveness of the algorithm in classifying network attacks from KDD Cup99 and 1998 DARPA dataset. SOFM ANN and GA training parameters werediscussed and implemented for performance evaluation. The experimentalresults demonstrated that SOFM ANN achieved better performance than GA,where in SOFM ANN high attack detection rate is 99.98 , 99.89 , 100 ,100 , 100 and low false positive rate is 0.01 , 0.1 , 0 , 0 , 0 for DoS,R2L, Probe, U2R attacks, and Normal traffic respectively.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×