Enhancing Network Intrusion Detection with Support Vector Machines: A Comparative Study of Feature Selection Techniques

This research investigates the impact of feature selection techniques on the performance of Support Vector Machine (SVM)-based Network Intrusion Detection Systems (NIDS). Using the SCVIC-APT-2021 dataset as a benchmark, this study evaluate the effects of different feature selection algorithms on detection accuracy, computational efficiency, and scalability. The research findings highlight the significance of choosing the appropriate feature selection algorithm for SVM-based NIDS. By understanding the strengths and weaknesses of various methods, researchers and practitioners can optimize their IDSes to effectively detect intruder attacks and safeguard network security from emerging internet threats. This study provides valuable insights into the optimization of SVM-based NIDS and contributes to the advancement of network security research.