{
  "added_at": "2026-10-20",
  "arxiv_id": "2609.14098",
  "arxiv_version_reviewed": "v2",
  "authors": [
    "Timo Schefold"
  ],
  "bibtex_url": "https://awesomerea.org/papers/citations/paper-deception-delta.bib",
  "code_url": null,
  "date_basis": "Official ACM CCS 2026 accepted-paper list confirms acceptance, not a publication date. The reviewed arXiv v2 revision is dated 2026-10-06.",
  "date_basis_zh": "ACM CCS 2026 官方接收名单确认录用，不能据此推定出版日期。审阅的 arXiv v2 修订日期为 2026-10-06。",
  "date_precision": "year",
  "description_en": "Evaluates how language models interpret raw EVM bytecode from purpose-built deceptive and control contracts. It distinguishes recognizing a hidden transfer mechanism from correctly judging its risk, using model judges alongside judge-independent checks.",
  "description_zh": "评估语言模型如何解释人工构造的欺骗性合约与对照合约的原始 EVM 字节码，区分识别隐藏转账机制与正确判断其风险，并结合模型评审和不依赖评审模型的检查。",
  "doi": "10.48550/arxiv.2609.14098",
  "entry_url": "https://awesomerea.org/papers/paper-deception-delta/",
  "entry_url_zh": "https://awesomerea.org/zh/papers/paper-deception-delta/",
  "evidence_urls": [
    "https://arxiv.org/abs/2609.14098",
    "https://arxiv.org/html/2609.14098v2",
    "https://api.datacite.org/dois/10.48550/arxiv.2609.14098",
    "https://www.sigsac.org/ccs/CCS2026/program/accepted-papers.html",
    "https://doi.org/10.5281/zenodo.22686323",
    "https://zenodo.org/records/23164989",
    "https://zenodo.org/api/records/22686323"
  ],
  "first_arxiv_date": "2026-09-12",
  "id": "paper-deception-delta",
  "json_url": "https://awesomerea.org/papers/paper-deception-delta/record.json",
  "kind": "research",
  "markdown_url": "https://awesomerea.org/papers/paper-deception-delta/index.md",
  "markdown_url_zh": "https://awesomerea.org/zh/papers/paper-deception-delta/index.md",
  "metadata_notes": "The official CCS list confirms the single-author title; arXiv v2 corrects the September v1. The manuscript prints ACM DOI 10.1145/3830454.3846626 and future conference details, but its Crossref lookup returned 404 during review; no publisher publication date or container fields are asserted. The DOI field is the separately registered arXiv DOI. Article and Zenodo metadata declare CC BY 4.0. The concept artifact resolves to record 23164989, v1.0.2, dated 2026-10-05; its metadata describes ERRATA and a 53,006,308-byte ZIP.",
  "metadata_notes_zh": "官方 CCS 名单确认单作者及标题；arXiv v2 对九月的 v1 作了修订。手稿列出 ACM DOI 10.1145/3830454.3846626 及尚未来临的会议安排，但本次 Crossref 查询返回 404，因此不填写出版方的出版日期或容器字段。DOI 字段使用已另行登记的 arXiv DOI。论文及 Zenodo 元数据声明 CC BY 4.0。产物概念链接解析到记录 23164989，版本 1.0.2、日期 2026-10-05；元数据说明存在勘误，ZIP 大小为 53,006,308 字节。",
  "pdf_url": "https://arxiv.org/pdf/2609.14098v2",
  "project_url": "https://zenodo.org/records/23164989",
  "publication_date": null,
  "publication_status": "conference-accepted",
  "record_type": "paper",
  "runtime_tested": false,
  "scope_limitations_en": "The main evaluation covers 22 models and 13 synthetic contracts using single-shot raw bytecode, without execution tools, source retrieval or on-chain context. Its 8,528 analyzed responses exclude refusals and pending runs. Gold labels come from one expert; some judges also belong to evaluated model families. Ground-truth checks vary across contracts, including owner/selector-only checks and no dedicated EVM tests for two injection variants. These results neither measure deployed-contract prevalence nor generalize to interactive reverse-engineering agents.",
  "scope_limitations_zh": "主要评测覆盖 22 个模型与 13 个合成合约，仅单轮提供原始字节码，不含执行工具、源码检索或链上上下文。8,528 条纳入分析的回答排除了拒答及待完成运行。金标准来自一位专家，部分评审模型与被测模型属于相同系列。各合约的真值检查不一致，包括仅检查所有者权限或选择器，以及两个注入变体没有专门 EVM 测试。结果不能估计真实部署合约中的发生率，也不能推广到交互式逆向智能体。",
  "targets": [
    "binary"
  ],
  "title": "The Deception Delta: Adversarial Evaluation of LLM-Based Smart Contract Bytecode Forensics",
  "title_zh": "Deception Delta：基于大语言模型的智能合约字节码取证对抗评测",
  "url": "https://arxiv.org/abs/2609.14098",
  "venue": "ACM CCS 2026",
  "verification": "source-reviewed",
  "verified_at": "2026-10-20",
  "why_fits_en": "Adds a bounded failure-mode evaluation for interpreting executable bytecode, especially the gap between describing behavior and assigning a trustworthy safety verdict.",
  "why_fits_zh": "为解释可执行字节码补充有明确边界的失效评测，尤其关注描述行为与给出可信安全判断之间的差距。",
  "year": 2026
}