用自然语言查二进制代码，实现精准匹配。
Cross-modal Retrieval Models for Stripped Binary Analysis
- 分两阶段构建跨模态检索框架，先嵌入后重排。
- 在Rec@3上比同类模型高31.42%，MRR@3高27.17%。
- 适合安全研究者做漏洞检测与恶意代码分析。
通过自然语言查询检索二进制代码是软件安全领域下游任务（如漏洞检测、恶意代码分析）的关键能力。由于缺乏符号信息，从数千个候选函数中识别语义相关的二进制函数极具挑战性。本文提出BinSeek，一种两阶段跨模态检索框架，包含两个模型：BinSeek-Embedding在大规模数据集上训练，学习二进制代码与自然语言描述之间的语义相关性；BinSeek-Reranker通过上下文增强，精细判断候选代码与描述的相关性。为此，我们构建了基于大语言模型的数据合成流水线，自动生成训练数据，并建立领域基准数据集以供未来研究。实验表明，BinSeek在Rec@3上优于同规模模型31.42%，在MRR@3上提升27.17%，且领先参数量大16倍的通用先进模型。
原文摘要 · Abstract (English)
Retrieving binary code via natural language queries is a pivotal capability for downstream tasks in the software security domain, such as vulnerability detection and malware analysis. However, it is challenging to identify binary functions semantically relevant to the user query from thousands of candidates, as the absence of symbolic information distinguishes this task from source code retrieval. In this paper, we introduce, BinSeek, a two-stage cross-modal retrieval framework for stripped binary code analysis. It consists of two models: BinSeek-Embedding is trained on large-scale dataset to learn the semantic relevance of the binary code and the natural language description, furthermore, BinSeek-Reranker learns to carefully judge the relevance of the candidate code to the description with context augmentation. To this end, we built an LLM-based data synthesis pipeline to automate training construction, also deriving a domain benchmark for future research. Our evaluation results show that BinSeek achieved the state-of-the-art performance, surpassing the the same scale models by 31.42% in Rec@3 and 27.17% in MRR@3, as well as leading the advanced general-purpose models that have 16 times larger parameters.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。