Toward Reducing IDS Misclassification Using Hybrid DL and ML Approach

Operation centers often face challenges due to the high rate of misclassifications caused by the lower precision in Intrusion Detection System (IDS) models. Despite several research contributions ranging from machine learning and deep learning techniques aiming to reduce false positives and negatives, researchers and security experts consistently encounter a tradeoff between these two types of errors. This indicates a significant opportunity for further contributions in this field. We propose a hybrid model that combines Recurrent Neural Networks (RNN) feature extraction capabilities with Support Vector Machines (SVM) classification abilities. Our model achieves an impressive accuracy rate of 98.2% and significantly reduces misclassification errors compared to contemporary state-of-the-art models. This work shows the potential of hybrid approaches in improving accuracy and reducing false positive and negative errors.