Robust Anomaly Detection in Network Traffic using Deep Learning Models

The exact detection of anomalies in computer network traffic is crucial to network protection. This study presents a novel approach to achieving the stated goal: the use of deep learning models. To correctly capture the temporal, geographic, and probabilistic aspects of network data, the recently developed approach integrates deep autoencoders (DAE), variable autoencoders (VAE), and long short-term memory (LSTM) networks. The proposed strategy surpassed six industry-standard solutions in terms of accuracy, recall, F1-score, AUC-ROC, false positive rate (FPR), and false negative rate (FNR). This was demonstrated via performance reviews. Furthermore, the proposed technique makes optimum use of currently available resources. This study improves network security by employing more robust anomaly detection algorithms.