Anomaly detection in encrypted HTTPS traffic using machine learning: a comparative analysis of feature selection techniques

With the increasing use of encryption in network traffic, anomaly detection in encrypted traffic has become a challenging problem. This study proposes an approach for anomaly detection in encrypted HTTPS traffic using machine learning and compares the performance of different feature selection techniques. The proposed approach uses a dataset of HTTPS traffic and applies various machine learning models for anomaly detection. The study evaluates the performance of the models using various evaluation metrics, including accuracy, precision, recall, F1-score, and area under the curve (AUC). The results show that the proposed approach with feature selection outperforms other existing techniques for anomaly detection in encrypted network traffic. However, the proposed approach has limitations, such as the need for further optimization and the use of a single dataset for evaluation. The study provides insights into the performance of different feature selection techniques and presents future research directions for improving the proposed approach. Overall, the proposed approach can aid in the development of more effective anomaly detection techniques in encrypted network traffic.