{
  "added_at": "2026-10-16",
  "arxiv_id": "2604.03750",
  "arxiv_version_reviewed": "v2",
  "authors": [
    "Baicheng Chen",
    "Yu Wang",
    "Ziheng Zhou",
    "Xiangru Liu",
    "Juanru Li",
    "Yilei Chen",
    "Tianxing He"
  ],
  "bibtex_url": "https://awesomerea.org/papers/citations/paper-crebench.bib",
  "code_url": "https://github.com/wangyu-ovo/CREBench",
  "date_basis": "Publication year from the official COLM 2026 OpenReview record and its BibTeX; no finer publication date is asserted.",
  "date_basis_zh": "采用 COLM 2026 官方 OpenReview 记录及其 BibTeX 标明的出版年份，不推定更精确的出版日期。",
  "date_precision": "year",
  "description_en": "Benchmarks cryptographic binary reverse engineering across algorithm recognition, key or IV extraction, wrapper reconstruction, and flag recovery using 432 controlled challenges.",
  "description_zh": "通过 432 个受控挑战，评估密码二进制逆向中的算法识别、密钥或 IV 提取、包装层重建及标志恢复。",
  "doi": null,
  "entry_url": "https://awesomerea.org/papers/paper-crebench/",
  "entry_url_zh": "https://awesomerea.org/zh/papers/paper-crebench/",
  "evidence_urls": [
    "https://openreview.net/forum?id=tLYdf8hWJB",
    "https://colm.cc/Conferences/2026/AcceptedPapers",
    "https://colm.cc/Conferences/2026",
    "https://arxiv.org/abs/2604.03750",
    "https://arxiv.org/html/2604.03750v2",
    "https://arxiv.org/pdf/2604.03750v2",
    "https://github.com/wangyu-ovo/CREBench",
    "https://github.com/wangyu-ovo/CREBench/blob/9fc4016538a0bab8c230732a9f788a61ed43addf/README.md",
    "https://jams-zhou-james.github.io/CREBench/"
  ],
  "first_arxiv_date": "2026-04-04",
  "id": "paper-crebench",
  "json_url": "https://awesomerea.org/papers/paper-crebench/record.json",
  "kind": "research",
  "markdown_url": "https://awesomerea.org/papers/paper-crebench/index.md",
  "markdown_url_zh": "https://awesomerea.org/zh/papers/paper-crebench/index.md",
  "metadata_notes": "The COLM 2026 OpenReview record has the same title, seven authors and abstract as arXiv v2 (2026-08-06), whose header reads 'Published as a conference paper at COLM 2026' and which the official project calls its camera-ready version. OpenReview’s 2026-07-08 publication timestamp coincides with the project’s acceptance announcement and is not used as a publication date; the October 6–9, 2026 conference and its Poster Session 5 listing are event details. The repository BibTeX still cites arXiv. This is unrelated to the creativity-evaluation paper also named CreBench.",
  "metadata_notes_zh": "COLM 2026 的 OpenReview 记录与 arXiv v2（2026-08-06）的标题、七位作者及摘要一致；v2 页首标注“Published as a conference paper at COLM 2026”，官方项目也说明其为会议终稿版本。OpenReview 记录的发布时间 2026-07-08 与项目公布接收的日期相同，不作为出版日期；2026 年 10 月 6—9 日的会议及第 5 场海报环节安排属于会议信息。仓库 BibTeX 仍采用 arXiv 引用。该工作与另一篇同名 CreBench 的创造力评估论文无关。",
  "pdf_url": "https://arxiv.org/pdf/2604.03750v2",
  "project_url": "https://jams-zhou-james.github.io/CREBench/",
  "publication_date": null,
  "publication_status": "conference-paper",
  "record_type": "paper",
  "runtime_tested": false,
  "scope_limitations_en": "The corpus combines 48 algorithms, three insecure key-use scenarios, and three difficulty levels. It excludes professional-grade obfuscators such as Tigress and O-LLVM; results should not be generalized to heavily protected arbitrary binaries.",
  "scope_limitations_zh": "语料组合 48 种算法、三类不安全密钥使用场景和三个难度等级。它不覆盖 Tigress、O-LLVM 等专业混淆器，结果不应推广到任意重度保护的二进制文件。",
  "targets": [
    "binary"
  ],
  "title": "CREBench: Evaluating Large Language Models in Cryptographic Binary Reverse Engineering",
  "title_zh": "CREBench：评估大语言模型的密码二进制逆向工程能力",
  "url": "https://openreview.net/forum?id=tLYdf8hWJB",
  "venue": "COLM 2026",
  "verification": "source-reviewed",
  "verified_at": "2026-10-17",
  "why_fits_en": "Provides a focused, decomposed test of cryptographic behavior recovery, with a verified official implementation.",
  "why_fits_zh": "对密码行为恢复提供细分、聚焦的测试，并有已确认的官方实现。",
  "year": 2026
}