Talk Like a Packet: Rethinking Network Traffic Analysis with Transformer Foundation Models

TL;DR

This paper explores the application of Transformer-based foundation models to network traffic analysis, demonstrating their effectiveness across multiple tasks and their advantage over traditional models.

Contribution

It introduces a unified pre-training and fine-tuning pipeline for traffic foundation models, showcasing their generalizability and improved performance in network analysis tasks.

Findings

Foundation models outperform non-foundation baselines.

Models effectively learn traffic representations with limited labeled data.

Unified pipeline enables versatile downstream task performance.

Abstract

Inspired by the success of Transformer-based models in natural language processing, this paper investigates their potential as foundation models for network traffic analysis. We propose a unified pre-training and fine-tuning pipeline for traffic foundation models. Through fine-tuning, we demonstrate the generalizability of the traffic foundation models in various downstream tasks, including traffic classification, traffic characteristic prediction, and traffic generation. We also compare against non-foundation baselines, demonstrating that the foundation-model backbones achieve improved performance. Moreover, we categorize existing models based on their architecture, input modality, and pre-training strategy. Our findings show that these models can effectively learn traffic representations and perform well with limited labeled datasets, highlighting their potential in future intelligent network analysis systems.