{
  "added_at": "2026-11-06",
  "arxiv_id": "2305.13483",
  "arxiv_version_reviewed": "v4",
  "authors": [
    "Qingkai Shi",
    "Xiangzhe Xu",
    "Xiangyu Zhang"
  ],
  "bibtex_url": "https://awesomerea.org/papers/citations/paper-protocol-format-state-machine.bib",
  "code_url": null,
  "date_basis": "First arXiv submission date.",
  "date_basis_zh": "arXiv 首次提交日期。",
  "date_precision": "day",
  "description_en": "The paper extracts protocol message formats from parser code by analyzing parsing loops as state machines. It evaluates format inference and the use of the extracted machines in protocol fuzzers.",
  "description_zh": "论文通过将解析循环分析为状态机，从解析器代码中提取协议消息格式，并评估格式推断效果及所提取状态机在协议模糊测试中的应用。",
  "doi": null,
  "entry_url": "https://awesomerea.org/papers/paper-protocol-format-state-machine/",
  "entry_url_zh": "https://awesomerea.org/zh/papers/paper-protocol-format-state-machine/",
  "evidence_urls": [
    "https://arxiv.org/abs/2305.13483"
  ],
  "first_arxiv_date": "2023-05-22",
  "id": "paper-protocol-format-state-machine",
  "json_url": "https://awesomerea.org/papers/paper-protocol-format-state-machine/record.json",
  "kind": "research",
  "markdown_url": "https://awesomerea.org/papers/paper-protocol-format-state-machine/index.md",
  "markdown_url_zh": "https://awesomerea.org/zh/papers/paper-protocol-format-state-machine/index.md",
  "metadata_notes": "The date and venue come from the arXiv record.",
  "metadata_notes_zh": "日期和发表场所来自 arXiv 记录。",
  "pdf_url": "https://arxiv.org/pdf/2305.13483",
  "project_url": null,
  "publication_date": "2023-05-22",
  "publication_status": "preprint",
  "record_type": "paper",
  "runtime_tested": false,
  "scope_limitations_en": "The analysis targets protocols with constraint-enhanced regular-expression formats parsed by finite-state machines. Reported results include over 90% precision and recall in five minutes, 20%–230% higher fuzzer coverage, and ten additional zero-days detected.",
  "scope_limitations_zh": "分析对象是格式由带约束的正则表达式描述、并由有限状态机解析的协议。报告的结果包括五分钟内超过90%的准确率和召回率、模糊测试覆盖率提高20%至230%，以及多发现十个零日漏洞。",
  "targets": [
    "protocol"
  ],
  "title": "Extracting Protocol Format as State Machine via Controlled Static Loop Analysis",
  "title_zh": "通过受控静态循环分析将协议格式提取为状态机",
  "url": "https://arxiv.org/abs/2305.13483",
  "venue": "arXiv",
  "verification": "source-reviewed",
  "verified_at": "2026-11-06",
  "why_fits_en": "It reverse engineers protocol message formats from parser implementations and uses the recovered state machines to improve fuzzing.",
  "why_fits_zh": "论文从解析器实现中逆向提取协议消息格式，并利用恢复的状态机改进模糊测试。",
  "year": 2023
}