Sakshi Agarwal
Independent Researcher
India
Abstract
Intrusion Detection Systems (IDS) are crucial for identifying unauthorized access and threats in computer networks. With the increasing complexity of cyber attacks, traditional IDS face challenges related to accuracy and computational efficiency. This manuscript presents an approach to enhance IDS performance by integrating Support Vector Machines (SVM) with feature selection techniques to reduce dimensionality and improve classification accuracy. Experimental results on standard datasets demonstrate that feature selection combined with SVM classification improves detection rate and reduces false positives. The proposed method shows promising results aligned with engineering practices prevalent up to 2021, focusing on balancing accuracy and computational overhead in IDS.
Keywords Intrusion Detection System, Support Vector Machine, Feature Selection, Cybersecurity, Network Security, Classification, Dimensionality Reduction
References
- Axelsson, S. (2000). Intrusion detection systems: A survey and taxonomy. Technical report, Chalmers University.
- Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine learning, 20(3), 273-297.
- Mukkamala, S., Sung, A. H., & Abraham, A. (2002). Intrusion detection using an ensemble of intelligent paradigms. Journal of Network and Computer Applications, 28(2), 167-182.
- Liu, H., & Motoda, H. (1998). Feature selection for knowledge discovery and data mining. Springer Science & Business Media.
- Zhang, Y., et al. (2011). Genetic algorithm-based feature selection for intrusion detection. Expert Systems with Applications, 38(10), 13184-13192.
- Amiri, A., Shamsuddin, S. M., & Hussain, A. (2013). Intrusion detection system: A comprehensive review. arXiv preprint arXiv:1309.0430.
