Unsupervised Dataset Cleaning Framework for Encrypted Traffic Classification

2025-08-31

AI Summary

Manual data cleaning in encrypted traffic classification is labor-intensive and poorly scalable. Method: This paper proposes an unsupervised, fully automated cleaning framework that jointly performs network flow feature extraction and anomaly pattern detection—eliminating irrelevant protocols, background noise, and long-lived sessions without per-packet human inspection. Contribution/Results: Evaluated on a real-world mobile encrypted traffic dataset, the framework incurs only a 2.0%–2.5% drop in classification accuracy compared to manual cleaning, while substantially accelerating preprocessing. To our knowledge, it is the first end-to-end, human-in-the-loop-free, unsupervised cleaning solution specifically designed for encrypted mobile traffic. The framework serves as an efficient, robust preprocessing module readily integrable into operational network traffic analysis systems.

Technology Category

• Machine Learning: Privacy
• Natural Language Processing: Safety and Robustness
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Web Mining and Content Analysis: Web data integration and cleaning
• Security and Privacy: Large-scale security measurements
• Responsible Web: Measurement, analysis, and circumvention of Web censorship

Abstract

Traffic classification, a technique for assigning network flows to predefined categories, has been widely deployed in enterprise and carrier networks. With the massive adoption of mobile devices, encryption is increasingly used in mobile applications to address privacy concerns. Consequently, traditional methods such as Deep Packet Inspection (DPI) fail to distinguish encrypted traffic. To tackle this challenge, Artificial Intelligence (AI), in particular Machine Learning (ML), has emerged as a promising solution for encrypted traffic classification. A crucial prerequisite for any ML-based approach is traffic data cleaning, which removes flows that are not useful for training (e.g., irrelevant protocols, background activity, control-plane messages, and long-lived sessions). Existing cleaning solutions depend on manual inspection of every captured packet, making the process both costly and time-consuming. In this poster, we present an unsupervised framework that automatically cleans encrypted mobile traffic. Evaluation on real-world datasets shows that our framework incurs only a 2%~2.5% reduction in classification accuracy compared with manual cleaning. These results demonstrate that our method offers an efficient and effective preprocessing step for ML-based encrypted traffic classification.

Problem

• Automatically cleans encrypted mobile traffic data
• Removes irrelevant flows for machine learning training
• Reduces manual inspection cost and time consumption

Innovation

• Unsupervised framework automates encrypted traffic cleaning
• Reduces manual inspection costs while maintaining accuracy
• Enables efficient preprocessing for ML classification