A Comparative Study of Different Relevant Features Hybrid Neural Networks Based Intrusion Detection Systems

Abstract:

Intrusion detection is the task of detecting, preventing and possibly reacting to the attacks and intrusions in a network based computer system. The neural network algorithms are popular for their ability to ’learn’ the so called patterns in a given environment. This feature can be used for intrusion detection, where the neural network can be trained to detect intrusions by recognizing patterns of an intrusion. In this work, we propose and compare the three different Relevant Features Hybrid Neural Networks based intrusion detection systems, where in, we first recognize the most relevant features for a connection record from a benchmark dataset and use these features in training the hybrid neural networks for intrusion detection. Performance of these three systems are evaluated on a well structured KDD CUP 99 dataset using a number of evaluation parameters such as classification rate, false positive rate, false negative rate etc.

• Periodical: Advanced Materials Research (Volumes 403-408)
• Pages: 4703-4710
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.403-408.4703
• Online since: November 2011
• Authors: Rashid Ali, Supriya Kamthania
• Keywords: Cascaded Forward Back Propagation (CFBP), Elman Back Propagation (ELBP), Intrusion Detection System (IDS), Multilayer Feed Forward (MLFF), Relevant Features Analysis, Self Organizing Feature Map (SOFM)

References

[1] KDD-cup' 99 dataset, http: /kdd. ics. uci. edu/databases/kddcup99/kddcup99. html.

[2] James Cannady and Jim Mahaffey, The application of Artificial Intelligence to Misuse Detection, in proceedings of the first Recent Advances in Intrusion Detection (RAID Conference), (1998).

[3] C. Jirapummin, N. Wattanapongsakorn and P. Kanthamanon, Hybrid Neural Networks for Intrusion Detection System, in the Proceedings of International Technical Conference on Circuits / Systems, Computers and Communications, (2002).

[4] DARPA Dataset documentation: http: /www. ll. mit. edu/IST/ideval/data/data_index. html.

[5] Alan Bivens, Chandrika Palagiri, Rasheda Smith, Boleslaw Szymanski and Mark Embrechts, Network Based Intrusion Detection using Neural Networks, in the proceedings of ANNIE Intelligent Engineering Systems through Artificial Neural Networks, (2002).

[6] P. Ganesh Kumar and D. Devaraj, Network Intrusion Detection using Hybrid Neural Networks, in the proceedings of IEEE International Conference on ICSCN, (2007).

[7] G. H. Kayacik and A. N. Zincir-Heywood, Selecting Features for Intrusion Detection: A Feature Relevance Analysis on KDD 99 Benchmark, in the Proceedings of the Third Annual Conference on Privacy, Security and Trust, St. Andrews, Canada, pp.62-69, (2005).

[8] The MathWorks-MATLAB and Simulink for Technical Computing, MATLAB online help http: /www. Mathworks. com/product/matlab/tryit. html.

DOI: 10.2514/5.9781600861628.0425.0428