Enhanced Network Anomaly Detection Using Hybrid Deep Learning Network Based on Interactive Threshold

In recent years, the growing use of the internet by both governments and private companies has led to a major increase in individual online activity. This expand lead to make the systems more effected to the threats and cyber attacks, and need more strong solutions to cyber security. Recently, deep learning (DL) and machine learning (ML) have become powerful tools in the cybersecurity field, especially for tasks such as detecting malware and filtering spam. This study present new multi layer method to detect the abnormal activities by busing advanced deep learning techniques. The proposed system work in tow main steps. The first one, using CNN model to classify data to normal and attack. This method use flexible threshold and updated at each training cycle to enhance detect accuracy. In the second stage, the data that the CNN marks as attacks are analyzed further by a Deep Neural Network (DNN) model, which identifies the specific type of attack. The system was tested using the KDD99 and CICIDS2017 datasets and achieved impressive accuracy rates of 99.3% for binary classification and 99.71% and 99.5% for multi-class classification. These results show the system's strong potential to improve network security.