{ "added_at": "2026-10-19", "arxiv_id": "2606.17398", "arxiv_version_reviewed": "v2", "authors": [ "Yujeong Kwon", "Yiyue Zhang", "Kexin Pei", "Dokyung Song", "Hyungjoon Koo" ], "bibtex_url": "https://awesomerea.org/papers/citations/paper-sok-ai-binary-reversing.bib", "code_url": null, "date_basis": "arXiv v1 submission; the reviewed v2 revision of 2026-09-04 does not change the first-submission date.", "date_basis_zh": "arXiv v1 首次提交日期；所审阅的 2026-09-04 v2 修订版不改变首次提交日期。", "date_precision": "day", "description_en": "A systematization-of-knowledge survey of machine-learning, LLM and agentic approaches to binary reversing. Version 2 collects 246 papers published since 2015, found through keyword searches of 11 security, software-engineering and AI venues plus citation snowballing, and organizes them into 22 domains by inference task: from code-boundary detection and recovery of function names, types and struct layouts to code similarity, malware and vulnerability analysis, and decompilation. Its taxonomy links conventional triage, static, dynamic and security-testing analyses to AI pipelines through the binary-derived artifacts they exchange, and it derives 12 insights and open directions such as binary-aligned ground truth and goal-driven agentic reversing.", "description_zh": "一篇系统化知识综述，梳理机器学习、大语言模型与智能体方法在二进制逆向中的应用。第二版通过关键词检索 11 个安全、软件工程与人工智能会议并辅以引文滚雪球，收集 2015 年以来的 246 篇论文，按推断任务归入 22 个领域：从代码边界检测，到函数名、类型与结构体布局恢复，再到代码相似性、恶意软件与漏洞分析以及反编译。其分类体系通过二进制派生的分析产物，把传统的初筛、静态分析、动态分析与安全测试同人工智能流程联系起来，并总结出 12 条洞见及若干开放方向，例如与二进制对齐的语义真值和目标驱动的智能体逆向。", "doi": null, "entry_url": "https://awesomerea.org/papers/paper-sok-ai-binary-reversing/", "entry_url_zh": "https://awesomerea.org/zh/papers/paper-sok-ai-binary-reversing/", "evidence_urls": [ "https://arxiv.org/abs/2606.17398v2", "https://arxiv.org/pdf/2606.17398v2", "https://arxiv.org/abs/2606.17398v1", "https://arxiv.org/pdf/2606.17398v1", "https://sok-aire.vercel.app" ], "first_arxiv_date": "2026-06-16", "id": "paper-sok-ai-binary-reversing", "json_url": "https://awesomerea.org/papers/paper-sok-ai-binary-reversing/record.json", "kind": "research", "markdown_url": "https://awesomerea.org/papers/paper-sok-ai-binary-reversing/index.md", "markdown_url_zh": "https://awesomerea.org/zh/papers/paper-sok-ai-binary-reversing/index.md", "metadata_notes": "Reviewed arXiv v2 (2026-09-04; comment “21 pages, 7 tables, 4 figures”), which lists five authors and 246 papers; this record follows the v2 author list. v1 (2026-06-16; “20 pages, 7 tables, 3 figures”) listed six authors, Yujeong Kwon, Yiyue Zhang, Shakhzod Yuldoshkhujaev, Kexin Pei, Dokyung Song and Hyungjoon Koo, and analyzed 144 papers published between 2015 and 2025. Neither version states a venue or journal reference. Footnote 1 in both versions links the companion site, an interactive JavaScript table of the surveyed papers grouped by domain with links to their publications; no source repository is linked. The site and its paper list may change after this review.", "metadata_notes_zh": "审阅 arXiv v2（2026-09-04；备注为“21 pages, 7 tables, 4 figures”），该版列出五位作者及 246 篇论文；本条目采用 v2 的作者列表。v1（2026-06-16；“20 pages, 7 tables, 3 figures”）列出六位作者：Yujeong Kwon、Yiyue Zhang、Shakhzod Yuldoshkhujaev、Kexin Pei、Dokyung Song 与 Hyungjoon Koo，并分析了 2015 至 2025 年发表的 144 篇论文。两个版本均未注明发表场所或期刊信息。两版的脚注 1 都链接到配套网站，这是一个按领域分组列出所综述论文并链接其出版页面的交互式 JavaScript 表格；未链接源码仓库。网站及其论文列表可能在本次审阅后变化。", "pdf_url": "https://arxiv.org/pdf/2606.17398v2", "project_url": "https://sok-aire.vercel.app", "publication_date": "2026-06-16", "publication_status": "preprint", "record_type": "paper", "runtime_tested": false, "scope_limitations_en": "A literature systematization with no new experiments, benchmark or tool; it classifies and summarizes reported results without reproducing them. The corpus covers papers available up to July 31, 2026, applies citation thresholds that fall from 12 for 2015–2016 papers to 2 for 2025–2026 papers, excludes methods that need source code at inference time, and leaves out Android and interpreted-language bytecode. Detailed per-stage tables draw on 88 top-venue studies rather than the full corpus. It is an arXiv preprint with no stated venue.", "scope_limitations_zh": "这是一篇文献系统化综述，不包含新的实验、基准或工具；它对已报告的结果进行分类和总结，并未复现。语料涵盖截至 2026 年 7 月 31 日可获得的论文，引用量门槛从 2015—2016 年论文的 12 次逐步降至 2025—2026 年论文的 2 次，排除推断时需要源码的方法，也不包括 Android 与解释型语言字节码。各阶段的详细表格基于 88 项顶级会议研究，而非完整语料。它是未注明发表场所的 arXiv 预印本。", "targets": [ "binary" ], "title": "SoK: AI-Augmented Binary Reversing", "title_zh": "SoK：人工智能增强的二进制逆向工程", "url": "https://arxiv.org/abs/2606.17398", "venue": "arXiv", "verification": "source-reviewed", "verified_at": "2026-10-18", "why_fits_en": "Provides a structured map of ML, LLM and agent research across binary reversing tasks, helping place the collection’s binary-analysis papers and locate related work that still needs individual review.", "why_fits_zh": "为跨二进制逆向任务的机器学习、大语言模型与智能体研究提供结构化地图，有助于定位本合集中的二进制分析论文，并找出仍需逐篇审阅的相关工作。", "year": 2026 }