arXiv cs.AI· Giampaolo Bovenzi, Domenico Ciuonzo, Jonatan Krolikowski, Antonio Montieri, Alfredo Nascita, Antonio Pescap\`e, Dario Rossi·· 3 小时前AI 评分41
轻量级 GenAI 用于网络流量生成：保真度、增强与分类研究
Lightweight GenAI for Network Traffic Generation: Fidelity, Augmentation, and Classification
AI 导读
一项研究探索用轻量级生成式 AI 架构进行网络流量生成（NTG），不生成原始数据包字节，而是基于早期包头信息合成紧凑的流级流量表示，使仅有几百万参数的 transformer、状态空间和扩散模型可用于该任务。研究沿保真度、纯合成数据训练、低数据量增强和计算效率四个维度评估该流水线，在两个异构数据集上的实验显示 transformer 模型保真度与效率权衡最佳。
正文 · 原文
Abstract:Network Traffic Classification (NTC) increasingly relies on data-driven models, yet its practical deployment is often constrained by limited labeled data, strict privacy requirements, and the cost of collecting representative traffic traces. 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 and often incur high computational costs. In this article, we investigate lightweight Generative Artificial Intelligence (GenAI) architectures for practical NTG. Rather than generating raw packet bytes or relying on large foundation models, we synthesize compact flow-level traffic representations derived from early packet-header information, enabling transformer-based, state-space, and diffusion models with only a few million parameters. We present a modular GenAI pipeline for NTG and evaluate it along four complementary axes: (i) synthetic traffic fidelity, (ii) synthetic-only training for reduced raw-data sharing in NTC, (iii) data augmentation under low-data regimes, and (iv) computational efficiency. Experiments on two heterogeneous datasets show that lightweight transformer-based and state-space models preserve both static and temporal traffic characteristics, while providing useful synthetic data for downstream NTC. Among them, transformer-based models offer the best fidelity-efficiency trade-off, combining high-quality traffic generation with moderate computational overhead.
| Comments: | 11 pages, 4 figures, 3 tables, 4 research questions, preprint submitted to Elsevier Computer Networks |
| Subjects: | Networking and Internet Architecture (cs.NI); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| ACM classes: | C.2.3; C.2.4; C.2.5; I.2.1; I.2.m |
| Cite as: | arXiv:2603.25507 [cs.NI] |
| (or arXiv:2603.25507v3 [cs.NI] for this version) | |
| https://doi.org/10.48550/arXiv.2603.25507 arXiv-issued DOI via DataCite |
Submission history
From: Antonio Montieri [view email]
[v1]
Thu, 26 Mar 2026 14:45:04 UTC (1,262 KB)
[v2]
Tue, 25 Aug 2026 11:59:01 UTC (1,510 KB)
[v3]
Wed, 11 Nov 2026 15:00:52 UTC (1,592 KB)
来源：arXiv cs.AI · arxiv.org