INTEGRATING NETWORK INTRUSION DETECTIONWITH MACHINE LEARNING TECHNIQUES FORENHANCED NETWORK SECURITY
Keywords:
Intrusion Detection Systems (IDS), Network Security, Fuzzy C-Means Clustering, K-Nearest Neighbor (KNN), Naïve Bayes (NB), Logistic Regression (LR), Stochastic Gradient Descent (SGD)Abstract
Cybersecurity attacks are more common than ever in today's globally networked society, which makes having strong intrusion detection systems (IDS) is essential. In this study, a hybrid IDS model is presented that combines fuzzy C-Means clustered with classification techniques including Naïve Bayes (NB), K-Nearest Neighbor (KNN), Logistic Regression (LR), and Stochastic Gradient Descent (SGD). To increase the accuracy of detection and resilience to changing cyberattacks, sophisticated feature selection approaches are used. The effectiveness of this method is confirmed through extensive testing with the NIDS dataset. By overcoming the limitations of conventional IDS, this study strengthens defenses against sophisticated assaults and uses machine learning to increase network security.
