研究发现协议过滤可提升 LLM 分析网络流量的准确率
Do LLMs Understand Network Traces? A Comparative Study of Reasoning over Raw and Filtered Traffic Data
搞网络运维的同学可以看看,这篇用 CICIDS2017 数据测了多个 LLM 解析流量的能力,结论很实用:先把流量按协议过滤再喂给模型,又省 token 又更准。
一篇发表于 arXiv 的研究评估了大语言模型在解析真实网络数据包方面的能力,使用的数据集是 CICIDS2017 中的良性流量样本。研究提出了一套可复现的问答式评估方法,让多个模型分别处理原始文本形式的流量转储和经过协议过滤后的表示,再与人工生成的标准答案比对。
技术流程上,模型回答通过 LLM-as-a-judge 自动化管线打分,该管线经过人工评估验证。结果显示,协议过滤在显著减少提示词开销的同时降低了错误回答数量,从而提高答题准确率。
对运维和安全团队而言,这项工作意味着把 LLM 引入流量分析时,先做协议感知的过滤是一个低成本、有效的优化手段,而非直接投喂原始 pcap 数据。
Do LLMs Understand Network Traces? A Comparative Study of Reasoning over Raw and Filtered Traffic Data
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.
本条情报归属 AITOP「论文」核心栏目,重点聚焦欧洲人工智能治理与技术生态。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:LLM、CICIDS2017、网络流量分析、LLM-as-a-judge,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明:本文原始线索采编自「arXiv cs.AI」(@Irene Gosálvez-White, Roberto Magán-Carrión, Carlota de la Vega-Soriano, Pedro García-Teodoro),经 AITOP 多维评分管线结构化提炼。