Research on Network Intrusion Detection Based on Support Vector Machine Optimized with Grasshopper Optimization Algorithm

As one of the most important parts of network security, more significance is attached to intrusion detection system (IDS). Numerous techniques including support vector machine (SVM) have been applied to the intrusion detection. However, many methods are utilized to improve the original SVM whose performance is markedly depended on its kernel parameters. Evolutionary algorithms such as genetic algorithm (GA) and particle swarm algorithm (PSO) are also employed to search better kernel parameters while the traditional optimization methods are vulnerable to fall into local minima with slow speed of convergence. In order to improve the precision of SVM in intrusion detection, the support vector machine based on grasshopper optimization algorithm (GOA-SVM) is proposed in the paper. To verify the practicality of the proposed method, several contrast experiments have been carried out using tool of Matlab. The experimental results finally demonstrates the superior performance of the proposed method on intrusion detection.

[1]  Andrew H. Sung,et al.  Feature Ranking and Selection for Intrusion Detection Using Artificial Neural Networks and Statistical Methods , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[2]  Jan H. P. Eloff,et al.  Personal Anomaly-based Intrusion Detection Smart Card Using Behavioural Analysis , 2007, SEC.

[3]  Dong Seong Kim,et al.  A Hybrid Approach for Real-Time Network Intrusion Detection Systems , 2007 .

[4]  Farid Melgani,et al.  Semisupervised PSO-SVM Regression for Biophysical Parameter Estimation , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[5]  Minh Le Nguyen,et al.  Feature weighting and SVM parameters optimization based on genetic algorithms for classification problems , 2016, Applied Intelligence.

[6]  Dong Seong Kim,et al.  Network-Based Intrusion Detection with Support Vector Machines , 2003, ICOIN.

[7]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[8]  Saswati Sarkar,et al.  A framework for misuse detection in ad hoc networks- part II , 2006, IEEE Journal on Selected Areas in Communications.

[9]  Jin-Kao Hao,et al.  A Hybrid GA/SVM Approach for Gene Selection and Classification of Microarray Data , 2006, EvoWorkshops.

[10]  Zied Elouedi,et al.  Naive Bayes vs decision trees in intrusion detection systems , 2004, SAC '04.

[11]  Hassan Ghassemian,et al.  A new fast algorithm for multiclass hyperspectral image classification with SVM , 2011 .

[12]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[13]  Hossam Faris,et al.  Simultaneous Feature Selection and Support Vector Machine Optimization Using the Grasshopper Optimization Algorithm , 2018, Cognitive Computation.

[14]  Hassan Ghassemian,et al.  A probabilistic SVM approach for hyperspectral image classification using spectral and texture features , 2017 .

[15]  Giovanni Vigna,et al.  Intrusion detection: a brief history and overview , 2002 .

[16]  Dorothy E. Denning,et al.  An Intrusion-Detection Model , 1986, 1986 IEEE Symposium on Security and Privacy.

[17]  Andrew Lewis,et al.  Grasshopper Optimisation Algorithm: Theory and application , 2017, Adv. Eng. Softw..

[18]  Dong Seong Kim,et al.  A Hybrid Approach for Real-Time Network Intrusion Detection Systems , 2007, 2007 International Conference on Computational Intelligence and Security (CIS 2007).

[19]  Ahmet Sertbas,et al.  Evaluation of face recognition techniques using PCA, wavelets and SVM , 2010, Expert Syst. Appl..

[20]  Sheng-Hsun Hsu,et al.  Application of SVM and ANN for intrusion detection , 2005, Comput. Oper. Res..

[21]  Hossam Faris,et al.  Grasshopper optimization algorithm for multi-objective optimization problems , 2017, Applied Intelligence.