ABSTRACT
In recent years, neural networks have been used to process network security data in intrusion detection, a process that is often highly nonlinear and strongly correlated. To address the problem that existing methods have high detection rates for known attack types, but have shortcomings in identifying emerging attack types, an intrusion detection (DBN-LSSVM) method combining a deep belief network (DBN) and a least-squares vector machine (LSSVM) is proposed. First, the original network dataset is pre-processed and the DBN is used to downscale the features of the dataset; then the PSO algorithm is used to optimize the input weights and implicit layer biases of LSSVM to establish an intrusion detection model; finally, simulation experiments are conducted on the KDD CUP 99 dataset. The experimental results show that compared with DBN-MSVM, DBN-BP, and SVM methods, the overall detection accuracy is significantly improved, and DBN-LSSVM has higher detection efficiency and better intrusion detection classification performance.
- Denning D E. An intrusion-detection model. IEEE Transactions on software engineering, 1987 (2), 222-232. https://doi.org/10.1109/TSE.1987.232894Google ScholarDigital Library
- Lee W, Stolfo S J, Mok K W. Adaptive intrusion detection: A data mining approach. Artificial Intelligence Review, 2000, 14(6), 533-567. https://doi.org/10.1023/A:1006624031083Google ScholarDigital Library
- Anderson J P. Computer security threat monitoring and surveillance. Technical Report, James P. Anderson Company, 1980.Google Scholar
- Singh J, Nene M J. A survey on machine learning techniques for intrusion detection systems. International Journal of Advanced Research in Computer and Communication Engineering, 2013, 2(11), 4349-4355.Google Scholar
- Hinton G E, Osindero S, Teh Y W. A fast learning algorithm for deep belief nets. Neural computation, 2006, 18(7), 1527-1554. https://doi.org/10.1162/neco.2006.18.7.1527Google ScholarDigital Library
- Nair V, Hinton GE. Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th international conference on international conference on machine learning. Haifa, Israel: Omnipress, 2010, 807–814. https://icml.cc/Conferences/2010/papers/432.pdfGoogle ScholarDigital Library
- Arsa D M S, Jati G, Mantau A J, Dimensionality reduction using deep belief network in big data case study: Hyperspectral image classification. 2016 International Workshop on Big Data and Information Security, IEEE, 2016, 71-76. https://doi.org/10.1109/IWBIS.2016.7872892Google ScholarCross Ref
- Yan Yan,Xu-Cheng Yin,Sujian Li,Mingyuan Yang,Hong-Wei Hao,Pasi A. Karjalainen. Learning Document Semantic Representation with Hybrid Deep Belief Network. Computational Intelligence and Neuroscience, 2015, 1-9. https://doi.org/10.1155/2015/650527Google Scholar
- Gao N, Gao L, Gao Q, An intrusion detection model based on deep belief networks. 2014 Second International Conference on Advanced Cloud and Big Data. IEEE, 2014, 247-252. https://doi.org/10.1109/CBD.2014.41Google ScholarCross Ref
- Nagaraj Balakrishnan, Arunkumar Rajendran, Danilo Pelusi,Vijayakumar Ponnusamy. Deep Belief Network enhanced Intrusion Detection System to Prevent Security Breach in the Internet of Things. Internet of Things, 2019. https://doi.org/10.1016/j.iot.2019.100112Google ScholarCross Ref
- Suykens J A K, Vandewalle J. Least squares support vector machine classifiers. Neural processing letters, 1999, 9(3), 293-300. https://doi.org/10.1023/A:1018628609742Google ScholarDigital Library
- Tavallaee M, Bagheri E, Lu W, A detailed analysis of the KDD CUP 99 data set. 2009 IEEE symposium on computational intelligence for security and defense applications. IEEE, 2009, 1-6. https://doi.org/10.1109/CISDA.2009.5356528Google ScholarCross Ref
- Gao N, He Y Y, Gao L. Deep learning method for intrusion detection in massive data. Applications Research of Computers, 2018, 35(4), 1197-1200.Google Scholar
- Cilimkovic M. Neural networks and back propagation algorithm. Institute of Technology Blanchardstown, Blanchardstown Road North Dublin, 2015, 15.Google Scholar
Recommendations
Research on intrusion detection method based on SMOTE and DBN-LSSVM
Aiming at the problems of low accuracy and high false alarm rate when traditional machine learning algorithm processes massive and complex intrusion detection data, this paper proposes a network intrusion detection method (SMOTE-DBN-LSSVM) which combines ...
The Design and Implementation of Host-Based Intrusion Detection System
IITSI '10: Proceedings of the 2010 Third International Symposium on Intelligent Information Technology and Security InformaticsIntrusion detection is the process of identifying and responding to suspicious activities targeted at computing and communication resources, and it has become the mainstream of information assurance as the dramatic increase in the number of attacks. ...
Intrusion Detection System Using Bagging Ensemble Method of Machine Learning
ICCUBEA '15: Proceedings of the 2015 International Conference on Computing Communication Control and AutomationIntrusion detection system is widely used to protect and reduce damage to information system. It protects virtual and physical computer networks against threats and vulnerabilities. Presently, machine learning techniques are widely extended to implement ...
Comments