Strengthening Cybersecurity using a Hybrid Classification Model with SCO Optimization for Enhanced Network Intrusion Detection System

Polymorphic malware and encrypted traffic hinder Network Intrusion Detection Systems (NIDS) from detecting complex attacks. Cybercriminals exploit NIDS algorithm vulnerabilities, showing how attack tactics and cybersecurity defenses change. This study suggests improving Network Intrusion Detection Systems. A thorough preprocessing phase with normalization functions improves data accuracy and consistency. The Single Candidate Optimization (SCO) feature selection algorithm optimizes NIDS efficacy. A hybrid model using Wavelet Transform, Long Short-Term Memory (LSTM), and Artificial Neural Networks (ANN) is used for classification because it can identify sequential dependencies in network traffic data. A second SCO iteration for hyperparameter tuning optimizes model performance and refines. The evaluation stage uses the BoT-IoT dataset, a prominent benchmark. SCO can improve hyperparameter optimization and feature selection to create a more accurate and cyberattack-resistant NIDS. The method's 99.6% accuracy is confirmed by experiments and performance evaluations. This shows how effective it is compared to current models, which strengthens cybersecurity defenses against changing attack landscapes. Similar trends are seen in the F1-scores, which range from 96.3% (ResNet50) to 99.4% (Proposed model). The Projected model performs exceptionally well in terms of stands out with the highest values in all metrics.