信息工程大学学报2026，Vol.27Issue(4)：436-442,7.DOI:10.3969/j.issn.1671-0673.2026.04.008
基于大语言模型推理增强的函数级二进制与源代码相似性检测
Function-Level Binary-to-Source Code Similarity Detection Method Enhanced by Large Language Model Reasoning
常金为 1孙佳佳 1尹小康 1张一筝 1朱肖雅 1李路凯1
作者信息
摘要
Abstract
Binary-to-source code similarity detection is widely used in software component analysis and vulnerability localization.However,existing methods struggle to align semantics across different modalities in complex compilation environments,leading to poor retrieval performance.To address these challenges,a similarity detection framework enhanced by Large Language Model reasoning(Bin-Think)is proposed.A Large Language Model is utilized in BinThink to construct a unified semantic representation of binary and source code functions,and a semantic guidance mechanism is combined to map functions from different modalities to the same vector space.Simultaneously,contrastive learn-ing is leveraged to optimize cross-modal semantic alignment,improving function retrieval performance in complex compilation environments.Experimental results show that,when the candidate pool size is 100,BinThink achieves Recall@1 improvements of 7.8 and 8.5 percentage points compared with the existing method BinaryAI in function retrieval tasks across compilation optimization and instruction ar-chitectures,respectively.关键词
二进制与源代码相似性检测/大语言模型/函数级推理增强/自适应推理/标准化语义流Key words
binary-to-source code similarity detection/Large Language Model/function-level reason-ing-enhancement/adaptive reasoning/standardized semantic flow分类
信息技术与安全科学引用本文复制引用
常金为,孙佳佳,尹小康,张一筝,朱肖雅,李路凯..基于大语言模型推理增强的函数级二进制与源代码相似性检测[J].信息工程大学学报,2026,27(4):436-442,7.
