Enhancing encrypted HTTPS traffic classification based on stacked deep ensembles models

Abstract

Abstract The classification of encrypted HTTPS traffic is a critical task for network management and security, where traditional port or payload-based methods are ineffective due to encryption and evolving traffic patterns. This study addresses the challenge using the public Kaggle dataset (145,671 flows, 88 features, six traffic categories: Download, Live Video, Music, Player, Upload, Website). An automated preprocessing pipeline is developed to detect the label column, normalize classes, perform a stratified 70/15/15 split into training, validation, and testing sets, and apply imbalance-aware weighting. Multiple deep learning architectures are benchmarked, including DNN, CNN, RNN, LSTM, and GRU, capturing different spatial and temporal patterns of traffic features. Experimental results show that CNN achieved the strongest single-model performance (Accuracy 0.9934, F1_macro 0.9912, ROC-AUC_macro 0.9999). To further improve robustness, a stacked ensemble meta-learner based on multinomial logistic regression was trained on model outputs, achieving state-of-the-art performance with Accuracy 0.9949, Precision_macro 0.9923, Recall_macro 0.9941, F1_macro 0.9932, and ROC-AUC_macro 0.9998. The framework also outputs confusion matrices, ROC curves, and learning curves for interpretability. To ensure reproducibility and practical use, the full codebase is publicly available on GitHub, providing researchers and practitioners with a deployment-ready pipeline for encrypted traffic analytics where ensemble learning surpasses individual models.