Hybrid Intrusion detection model-based density clustering approach and deep learning for detection of malicious traffic over network

Intrusion detection in modern network environments poses significant challenges due to the increasing volume and complexity of cyber-attacks. This study proposes a hybrid approach integrating density-based clustering with deep learning to identify malicious traffic over the network. The proposed framework consists of two steps: clustering and classifying data. in clustering, the proposed model uses density clustering techniques to pre-process and segment network traffic into coherent clusters, thereby reducing data noise within clusters. The deep learning model analyses these clusters, accurately distinguishing between benign and malicious activities. The proposed model was tested over the benchmark dataset CIRA-CIC-DoHBrw-2020. The performance of the proposed model compared with standard machine learning models and the number of states of the artworks. The experiment result demonstrates that our hybrid model significantly improves detection accuracy and reduces false-positive rates compared to existing methods .