ICTACT Journal on Soft Computing

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Improved Intrusion Detection Classifier using Cuckoo Search Optimization with Support Vector Machine


Affiliations
1 Department of Computer Science and Engineering, Sri Guru Institute of Technology, India
2 Department of Electronics and Communication Engineering, Siddhartha Institute of Technology, India
     

   Subscribe/Renew Journal


This paper proposes Cuckoo Search Optimization (CSO) with Support Vector Machine (SVM) for the intrusion detection system (IDS). This work covers modules including preprocessing, feature selection and classification. The pre-processing is carried out using min-maximum standardization to remove missing values and filter the redundancy characteristics from the specified NSL KDD cup data set. Preprocessing helps primarily to increase the accuracy of the description. Instead CSO is used to pick the most suitable and optimum functions. With CSO, the search efficiency is improved and then the analysis is carried out more effectively to classify the intrusions using the SVM algorithm. This classification algorithm is used to increase the accuracy of attack detection. The test results show that the CSO with SVM algorithm is more efficient than existing methods.

Keywords

Intrusion Detection, Feature Selection, SVM, CSO.
Subscription Login to verify subscription
User
Notifications
Font Size

  • Y. Zhao, “Network Intrusion Detection System Model based on Data Mining”, Proceedings of IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, pp. 1123-1129, 2016.

  • O. Koucham, T. Rachidi and A. Nasser, “Host Intrusion Detection using System Call Argument-based Clustering Combined with Bayesian Classification”, Proceedings of IEEE International Conference on Intelligent Systems, pp. 1-8, 2015.

  • S. Babu Devasenapati and K.I. Ramachandran, “Random Forest based Misfire Detection using Kononenko Discretiser”, ICTACT Journal of Soft Computing, Vol. 2, No. 2, pp. 270-275, 2012.

  • D. Amutha Guka, “Anomaly Detection in Networking using Hybrid Artificial Immune Algorithm”, ICTACT Journal of Soft Computing, Vol. 2, No. 2, pp. 298-304, 2012

  • S. Noel and S. Jajodia, “Advanced Vulnerability Analysis and Intrusion Detection through Predictive Attack Graphs”, Proceedings of IEEE International Conference on Armed Forces Communications and Electronics Association Solutions Series, pp. 1-10, 2009.

  • Safaa Zaman, Mohammed El Abed and Fakhri Karray. “Features Selection Approaches for Intrusion Detection Systems Based on Evolution Algorithms”, Proceedings of 7th International Conference on Ubiquitous Information Management and Communication, pp. 1-7, 2013.

  • Amira Sayed A. Aziz, Aboul Ella Hassanien and Ahmad Thaer Azar, “Genetic Algorithm with Different Feature Selection Techniques for Anomaly Detectors Generation”, Proceedings of IEEE International Conference on Computer Science and Information Systems, pp. 8-11, 2013.

  • M. Moradi and M. Zulkernine. “A Neural Network based System for Intrusion Detection and Classification of Attacks”, Proceedings of IEEE International Conference on Advances in Intelligent Systems-Theory and Applications, pp. 1-12, 2004.

  • M.A. Ambusaidi, X. He, Z. Tan, P. Nada, L.F. Nu and U.T. Nagar, “A Novel Feature Selection Approach for Intrusion Detection Data Classification”, Proceedings of IEEE International Conference on Trust, Security and Privacy in Computing and Communications, pp. 1-8, 2014.

  • Y. Kumar and S.K. Bhandare, “Min Max Normalization based Data Perturbation Method for Privacy Protection”, International Journal of Computer and Communication Technology, Vo. 2, No. 8, pp. 45-50, 2011.

  • W. Hu and S. Maybank, “Adaboost-based Algorithm for Network Intrusion Detection”, IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, Vol. 38, No. 2, pp. 577-583. 2008.


Abstract Views: 250

PDF Views: 0




  • Improved Intrusion Detection Classifier using Cuckoo Search Optimization with Support Vector Machine

Abstract Views: 250  |  PDF Views: 0

Authors

D. Viknesh Kumar
Department of Computer Science and Engineering, Sri Guru Institute of Technology, India
Velmani Ramasamy
Department of Electronics and Communication Engineering, Siddhartha Institute of Technology, India

Abstract


This paper proposes Cuckoo Search Optimization (CSO) with Support Vector Machine (SVM) for the intrusion detection system (IDS). This work covers modules including preprocessing, feature selection and classification. The pre-processing is carried out using min-maximum standardization to remove missing values and filter the redundancy characteristics from the specified NSL KDD cup data set. Preprocessing helps primarily to increase the accuracy of the description. Instead CSO is used to pick the most suitable and optimum functions. With CSO, the search efficiency is improved and then the analysis is carried out more effectively to classify the intrusions using the SVM algorithm. This classification algorithm is used to increase the accuracy of attack detection. The test results show that the CSO with SVM algorithm is more efficient than existing methods.

Keywords


Intrusion Detection, Feature Selection, SVM, CSO.

References