arXiv cs.AI· Giampaolo Bovenzi, Domenico Ciuonzo, Jonatan Krolikowski, Antonio Montieri, Alfredo Nascita, Antonio Pescap\`e, Dario Rossi·· 1 天前AI 评分20
轻量级 GenAI 用于网络流量生成：保真度、增强与分类
Lightweight GenAI for Network Traffic Generation: Fidelity, Augmentation, and Classification
AI 导读
研究提出一套模块化轻量级 GenAI 流程，用早期包头信息合成紧凑的流级流量表示，使 Transformer、状态空间和扩散模型仅需几百万参数即可生成网络流量。在两个异构数据集上，轻量 Transformer 与状态空间模型能保留流量的静态与时序特征，并为下游网络流量分类提供有用的合成数据；其中 Transformer 在保真度与效率之间取得最佳平衡。
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