Lightweight GenAI for Network Traffic Synthesis: Fidelity, Augmentation, and Classification

TL;DR

This paper introduces lightweight GenAI models for network traffic synthesis that effectively preserve traffic characteristics, enhance classification accuracy with synthetic data, and operate efficiently for practical deployment.

Contribution

It presents novel lightweight transformer, state-space, and diffusion models for network traffic generation, addressing fidelity and efficiency challenges in practical scenarios.

Findings

Transformer and state-space models closely match real traffic distributions.

Synthetic-only training achieves up to 87% F1-score on real data.

Data augmentation improves NTC performance by up to 40% in low-data regimes.

Abstract

Accurate Network Traffic Classification (NTC) is increasingly constrained by limited labeled data and strict privacy requirements. While Network Traffic Generation (NTG) provides an effective means to mitigate data scarcity, conventional generative methods struggle to model the complex temporal dynamics of modern traffic or/and often incur significant computational cost. In this article, we address the NTG task using lightweight Generative Artificial Intelligence (GenAI) architectures, including transformer-based, state-space, and diffusion models designed for practical deployment. We conduct a systematic evaluation along four axes: (i) (synthetic) traffic fidelity, (ii) synthetic-only training, (iii) data augmentation under low-data regimes, and (iv) computational efficiency. Experiments on two heterogeneous datasets show that lightweight GenAI models preserve both static and temporal traffic characteristics, with transformer and state-space models closely matching real distributions across a complete set of fidelity metrics. Classifiers trained solely on synthetic traffic achieve up to 87% F1-score on real data. In low-data settings, GenAI-driven augmentation improves NTC performance by up to +40%, substantially reducing the gap with full-data training. Overall, transformer-based models provide the best trade-off between fidelity and efficiency, enabling high-quality, privacy-aware traffic synthesis with modest computational overhead.