paperbot · PL 论文追踪

全部论文 待读 收藏

P2 RFCScope: Detecting Logical Ambiguities in Internet Protocol Specifications

RFCScope:检测互联网协议规范中的逻辑歧义
ASE 2025 40th IEEE/ACM International Conference on Automated Software Engineering (ASE)2025匹配度 4/10 · 该论文利用 LLM 检测 RFC 规范中的逻辑歧义,属于规范分析与 LLM 的交叉,与“LLM/Agent 改进静态分析/形式化验证”仅间接相关;不涉及程序分析、浮点程序分析、贝叶斯程序分析或 Agentic 程序,核心场景是网络协议规范而非 PL/程序验证。引用 0 inbox
Mrigank Pawagi, Lize Shao, Hyeonmin Lee, Yixin Sun, Wenxi Wang
crossref: 2026-09-12

AI 速览

一句话:首次系统研究 RFC 逻辑歧义,并提出基于 LLM 的可扩展检测框架,发现 31 处新歧义。

互联网协议以 IETF RFC 形式发布,其中的逻辑歧义(不一致与欠规范)会导致实现错误,但现有工具难以检测。本文首先系统分析过去 11 年 Standards Track RFC 的已验证技术勘误,归纳出七类逻辑歧义。在此基础上提出 RFCScope:一个基于大语言模型的可扩展检测框架,通过构建跨文档上下文、保持语义完整性的规范切分、面向缺陷类型的提示以及结构化推理验证来减少误报。RFCScope 在 14 个近期 RFC 中发现 31 个新逻辑歧义,覆盖全部七类;其中 8 个获作者确认,3 个被正式验证为技术勘误。

问题
RFC 规范中的逻辑歧义(如不一致与欠规范)易导致解读错误和实现缺陷,但现有工具难以检测,且缺乏系统研究。
方法
先对过去 11 年 Standards Track RFC 的已验证技术勘误进行系统研究,归纳七类逻辑歧义;再提出基于 LLM 的模块化流水线,包括跨文档上下文构建、语义保持切分、缺陷类型感知提示与结构化推理验证。
评估
在 14 个近期 RFC 上发现 31 个新逻辑歧义,覆盖全部七类;8 个获 RFC 作者确认,3 个被官方验证为技术勘误。
原文摘要(Abstract)

Internet protocol specifications, published as Requests for Comments (RFCs) by the IETF organization, are essential to ensuring the interoperability, security, and reliability of the Internet. However, ambiguities in these specifications, particularly logical ambiguities such as inconsistencies and under-specifications, can lead to critical misinterpretations and implementation errors. Unfortunately, such ambiguities remain largely overlooked and challenging to detect with existing tools.In this paper, we present the first systematic study of verified technical errata from Standards Track RFCs over the past 11 years, identifying seven distinct subtypes of logical ambiguities. Building on these insights, we introduce RFCScope, the first scalable framework for detecting logical ambiguities in RFCs. RFCScope employs large language models (LLMs) through a modular pipeline that constructs targeted cross-document context, partitions specifications to preserve semantic integrity, applies bug-type-aware prompts for detection, and filters out false positives using structured reasoning validation.RFCScope uncovers 31 new logical ambiguities spanning all seven subtypes across 14 recent RFCs. Eight of these have been confirmed by RFC authors, with three officially verified as technical errata. Our results demonstrate that RFCScope offers a practical solution for improving the clarity, consistency, and reliability of protocol standards through ambiguity detection.

链接与引用

DOI 原文 ·

BibTeX
@inproceedings{paperbot9558,
  title = {RFCScope: Detecting Logical Ambiguities in Internet Protocol Specifications},
  author = {Mrigank Pawagi and Lize Shao and Hyeonmin Lee and Yixin Sun and Wenxi Wang},
  booktitle = {ASE},
  year = {2025},
  doi = {10.1109/ase63991.2025.00106}
}