PACC: Protocol-Aware Cross-Layer Compression for Compact Network Traffic Representation

2026-02-09

AI Summary

Amid the widespread adoption of encryption and evolving network protocols, representing network traffic entails a fundamental trade-off between compactness and cross-layer semantic completeness. This work proposes PACC, a novel framework that explicitly models both intra- and inter-layer redundancies within the protocol stack by decomposing traffic into shared and private components. Through a joint optimization of multi-view representation learning, contrastive mutual information maximization, hierarchical reconstruction, and task-aware supervision, PACC learns compact representations that balance information fidelity with compression efficiency. Evaluated on encrypted application classification, IoT device identification, and intrusion detection tasks, PACC achieves up to a 12.9% improvement in accuracy and a 3.16× gain in inference efficiency, significantly outperforming baselines based on handcrafted features, raw packet bits, and large models.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Representation Learning for Vision
• Search and Optimization: Learning to Search

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Network traffic classification is a core primitive for network security and management, yet it is increasingly challenged by pervasive encryption and evolving protocols. A central bottleneck is representation: hand-crafted flow statistics are efficient but often too lossy, raw-bit encodings can be accurate but are costly, and recent pre-trained embeddings provide transfer but frequently flatten the protocol stack and entangle signals across layers. We observe that real traffic contains substantial redundancy both across network layers and within each layer; existing paradigms do not explicitly identify and remove this redundancy, leading to wasted capacity, shortcut learning, and degraded generalization. To address this, we propose PACC, a redundancy-aware, layer-aware representation framework. PACC treats the protocol stack as multi-view inputs and learns compact layer-wise projections that remain faithful to each layer while explicitly factorizing representations into shared (cross-layer) and private (layer-specific) components. We operationalize these goals with a joint objective that preserves layer-specific information via reconstruction, captures shared structure via contrastive mutual-information learning, and maximizes task-relevant information via supervised losses, yielding compact latents suitable for efficient inference. Across datasets covering encrypted application classification, IoT device identification, and intrusion detection, PACC consistently outperforms feature-engineered and raw-bit baselines. On encrypted subsets, it achieves up to a 12.9% accuracy improvement over nPrint. PACC matches or surpasses strong foundation-model baselines. At the same time, it improves end-to-end efficiency by up to 3.16x.

Problem

• network traffic classification
• protocol-aware representation
• cross-layer redundancy
• encrypted traffic
• compact representation

Innovation

• cross-layer compression
• protocol-aware representation
• redundancy-aware learning
• multi-view network traffic
• compact latent representation