arXiv：cs.LG（机器学习，全量分类）· Shenghe Xu, Lifan Mei·· 14 小时前AI 评分28
Jev 用于网络流量分类的首个实证研究：准确率、处理时间与成本
A First Glance at Jev for Network Traffic Classification: Accuracy, Processing Time, and Cost
AI 导读
研究首次实证评估通用决策模型 Jev 在网络流量应用分类上的表现：在 CESNET-QUICEXT-25 数据集上仅用前 10 个数据包的包大小、方向和包间隔时间，40 个固定标注样本将 Jev 准确率从 9.80% 提升至 28.42%，上下文增至 150 个样本时首个测试周达 34.50%。
正文
Abstract:We evaluate Jev on ten dataset-defined application labels in CESNET-QUICEXT-25 using only the first ten packets' sizes, directions, and inter-packet times. To the best of our knowledge, this is the first empirical study of general-purpose decision models, represented here by Jev, for application classification of network flows. Across 52,000 records from 26 collection weeks following the training period, 40 fixed labeled examples raise Jev's accuracy from 9.80% to 28.42%. Random Forest and Extra Trees trained on 8,000 records achieve 69.95% and 66.80% and outperform Jev in every week. Increasing Jev's context to 150 examples yields 34.50% on the first test week. On a paired 100-record subset, Jev with 40 examples achieves 29% accuracy at a median request time of 0.750 s, versus 37% and 6.036 s for the generative language model OpenAI GPT-5.6 Sol with high reasoning effort through Azure; Jev also incurs lower API charges. The paired subset does not establish an accuracy advantage for either service, and the timing reflects different service configurations. Thus, labeled examples substantially improve Jev, but the tested Jev configurations remain less accurate than trained tree ensembles; unequal supervision budgets and fixed configurations prevent attributing the gap to a single cause.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.00376 [cs.LG] |
| (or arXiv:2610.00376v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.00376 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Lifan Mei [view email]
[v1]
Wed, 30 Sep 2026 08:21:44 UTC (48 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org