Distillation-Enhanced Clustering Acceleration for Encrypted Traffic Classification

TL;DR

This paper introduces NetClus, a framework that accelerates encrypted traffic classification by combining pretrained models with distillation and clustering, enabling faster inference and detection of new traffic types with minimal accuracy loss.

Contribution

NetClus integrates distillation-enhanced clustering with pretrained models to accelerate encrypted traffic classification and improve detection of emerging traffic types.

Findings

Achieves up to 6.2x speedup over existing methods.

Maintains classification accuracy with less than 1% degradation.

Effectively identifies new traffic types using proposed metrics.

Abstract

Traffic classification plays a significant role in network service management. The advancement of deep learning has established pretrained models as a robust approach for this task. However, contemporary encrypted traffic classification systems face dual limitations. Firstly, pretrained models typically exhibit large-scale architectures, where their extensive parameterization results in slow inference speeds and high computational latency. Secondly, reliance on labeled data for fine-tuning restricts these models to predefined supervised classes, creating a bottleneck when novel traffic types emerge in the evolving Internet landscape. To address these challenges, we propose NetClus, a novel framework integrating pretrained models with distillation-enhanced clustering acceleration. During fine-tuning, NetClus first introduces a cluster-friendly loss to jointly reshape the latent space for both classification and clustering. With the fine-tuned model, it distills the model into a lightweight Feed-Forward Neural Network model to retain semantics. During inference, NetClus performs heuristic merge with near-linear runtime, and valid the cluster purity with newly proposed metrics ASI to identify emergent traffic types while expediting classification. Benchmarked against existing pretrained methods, NetClus achieves up to 6.2x acceleration while maintaining classification degradation below 1%.