RustMizan：用于Rust漏洞的可编译、污染感知基准测试框架
RustMizan: A Compilable, Contamination-Aware Benchmarking Framework for Rust Vulnerabilities
AI总结：
针对现有Rust漏洞分析基准不足，介绍RustMizan框架，含可编译代码变体及注释，用配对突变框架测试，给出不同模型在该框架下的测试结果。
摘要：
大语言模型代理越来越多地应用于漏洞分析，但现有基准未能跟上。它们通常依赖小型不可编译代码片段，专注于二进制分类，且未考虑公开数据集成为模型训练语料库一部分的风险。我们引入RustMizan，一个用于Rust漏洞分析的基准测试框架，解决了这些差距。RustMizan包含在crate、文件和函数级别可编译的代码变体，带有用于二进制漏洞检测、CWE分类以及函数和行级定位的注释。一个配对突变框架生成用于污染测试和鲁棒性探测的语义保留代码突变体。在具有命令行访问权限的代理设置中的四个前沿模型中，二进制分类在56 - 65%范围内，但行定位F1接近20%，对抗性线索使行F1下降约27%。
英文摘要：
LLM agents are increasingly applied to vulnerability analysis, but existing benchmarks have not kept pace. They typically rely on small non-compilable snippets, focus on binary classification (vulnerable or not), and do not account for the risk that publicly-released datasets are part of model training corpora. We introduce RustMizan, a benchmarking framework for Rust vulnerability analysis that addresses these gaps. RustMizan contains compilable code variants at the crate, file, and function levels, with annotations for binary vulnerability detection, CWE classification, and function- and line-level localization. A paired mutation framework produces semantics-preserving code mutants for contamination testing and robustness probing. Across four frontier models in an agentic setup with command-line access, binary classification sits in the 56-65% range, but line localization F1 stays near 20%, and adversarial cues drop line F1 by about 27%.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
