paperbot · PL 论文追踪

全部论文 待读 收藏

P1 Oracle-Guided Vulnerability Diversity and Exploit Synthesis of Smart Contracts Using LLMs

基于LLM的预言机引导智能合约漏洞多样性与漏洞利用合成
ASE Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering2024匹配度 5/10 · 该论文用业务逻辑的 oracle 规约引导 LLM 合成智能合约漏洞利用,属于“LLM 辅助程序分析/漏洞发现”这一 AI→PL 方向的邻近工作,且问题驱动明确(指出现有数据集 ground truth 不可靠、只覆盖低级漏洞、缺具体 exploit),与用户对 benchmark 缺陷与规约引导的兴趣部分契合;但它聚焦智能合约安全与 exploit 合成,既不涉及静态分析工具本身的改进(尤其非 ML/Agentic 程序),也不涉及浮点或贝叶斯程序分析,交叉点较窄。引用 2 inbox
Mojtaba Eshghie, Cyrille Artho
crossref: 2026-09-12

AI 速览

一句话:提出XploGen,用业务逻辑的oracle规约引导LLM合成智能合约漏洞利用,兼顾多样性与具体exploit示例。

智能合约漏洞分析工具常在有限数据集上训练和评估,存在三方面缺陷:ground truth 多依赖同类工具的判定而非真实验证结果;数据集集中于重入、溢出等低级漏洞;且缺少具体漏洞利用示例。为此,作者提出 XploGen,用基于模型的 oracle 规约刻画合约业务逻辑,并借助 LLM 合成针对性的有效漏洞利用。实验构建了 104 个合成漏洞-利用对,在合约特定方面的利用成功率达 57%,且每个利用平均仅需 3.5 笔交易,表明该方法能以较高效率生成多样且具体的漏洞利用。

问题
现有智能合约漏洞数据集规模有限,ground truth 依赖工具判定、只覆盖低级漏洞且缺乏具体 exploit 示例。
方法
提出 XploGen,用业务逻辑的模型化 oracle 规约引导 LLM 合成有效且多样的漏洞利用。
评估
在 104 个合成漏洞-exploit 对上评估,针对性利用成功率达 57%,平均每个 exploit 仅 3.5 笔交易。
原文摘要(Abstract)

Many smart contracts are prone to exploits, which has given rise to analysis tools that try to detect and fix vulnerabilities. Such analysis tools are often trained and evaluated on limited data sets, which has the following drawbacks: 1. The ground truth is often based on the verdict of related tools rather than an actual verification result; 2. Data sets focus on low-level vulnerabilities like reentrancy and overflow; 3. Data sets lack concrete exploit examples. To address these shortcomings, we introduce XploGen, which uses a model-based oracle specification of the business logic of the smart contracts to synthesize valid exploits using LLMs. Our experiments, involving 104 synthesized vulnerability-exploit pairs, demonstrated a 57% success rate in exploiting targeted aspects of the contract. They achieved exploit efficiency with an average of only 3.5 transactions per exploit, highlighting the effectiveness of our methodology.

链接与引用

DOI 原文 · PDF(开放获取) ·

BibTeX
@inproceedings{paperbot8363,
  title = {Oracle-Guided Vulnerability Diversity and Exploit Synthesis of Smart Contracts Using LLMs},
  author = {Mojtaba Eshghie and Cyrille Artho},
  booktitle = {ASE},
  year = {2024},
  doi = {10.1145/3691620.3695292}
}