arXiv cs.AI· Irene Gos\'alvez-White, Roberto Mag\'an-Carri\'on, Carlota de la Vega-Soriano, Pedro Garc\'ia-Teodoro·· 2 小时前AI 评分32
LLM 能否理解网络流量 traces?原始与过滤流量数据上的推理对比研究
Do LLMs Understand Network Traces? A Comparative Study of Reasoning over Raw and Filtered Traffic Data
AI 导读
一项提交至 NOMS2027 的研究提出可复现的问答式评估方法,检验 LLM 分析网络流量的能力,使用 CICIDS2017 数据集的真实良性流量与人工标注真值对比,并通过经人工验证的 LLM-as-a-judge 自动化流水线评估多个模型。结果显示,协议过滤显著降低了提示词开销,并通过减少错误回答提高了准确率。
正文 · 原文
Abstract:The effective delivery and monitoring of ICT services rely heavily on network traffic analysis. However, interpreting complex packet captures remains a challenging task that requires substantial technical expertise. Large language models (LLMs) offer promising opportunities to automate network traffic in- vestigation, yet their reliability in packet-level field extraction and flow-level sequence reconstruction remains an open research question. This study proposes a reproducible, question-answering- based evaluation methodology to assess the capabilities of LLMs in network trace analysis. Using real-world benign traffic from the CICIDS2017 dataset, we evaluate multiple models against a human-generated ground truth, comparing their performance on raw textual traffic dumps and protocol-filtered representations. Model responses are assessed through an automated LLM- as-a-judge pipeline, validated against human evaluations. The results demonstrate that protocol filtering significantly reduces prompt overhead while improving answer accuracy by reducing incorrect responses. These findings highlight the importance of protocol-aware traffic filtering as an effective optimization for improving the efficiency and reliability of LLM-assisted network management.
| Comments: | This publication has been submitted to NOMS2027 |
| Subjects: | Networking and Internet Architecture (cs.NI); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.22575 [cs.NI] |
| (or arXiv:2611.22575v1 [cs.NI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.22575 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Roberto Magán-Carrión Dr. [view email]
[v1]
Tue, 17 Nov 2026 11:00:59 UTC (1,306 KB)
来源:arXiv cs.AI · arxiv.org