一句话：首个大规模实证研究，构建两个高质量数据集，评估九种 AI 二进制函数相似性检测工具并提出组合策略。
二进制函数相似性检测（BFSD）是漏洞检测与恶意软件分析的基础技术。现有 AI 基 BFSD 工具评估存在三个局限：缺乏性能影响因素深入分析、缺少真实应用分析、依赖小规模或低质量数据集。本文开展首个大规模实证研究，构建两个高质量多样化数据集：BinAtlas 含 12,453 个二进制文件与超 700 万函数，用于能力评估；BinAres 含 12,291 个二进制文件与 54 个真实 1-day 漏洞，用于 IoT 固件场景下的漏洞检测评估。基于这些数据集，作者评估了九种代表性 BFSD 工具，分析现有工具的挑战与局限，并研究工具间一致性。最后提出可操作的组合策略，使整体性能提升 13.4%。该研究为可扩展自动化二进制相似性检测的实践与后续研究提供了资源与洞见。
Binary Function Similarity Detection (BFSD) is a foundational technique in software security, underpinning a wide range of applications including vulnerability detection, malware analysis. Recent advances in AI-based BFSD tools have led to significant performance improvements. However, existing evaluations of these tools suffer from three key limitations: a lack of in-depth analysis of performance-influencing factors, an absence of realistic application analysis, and reliance on small-scale or low-quality datasets.In this paper, we present the first large-scale empirical study of AI-based BFSD tools to address these gaps. We construct two high-quality and diverse datasets: BinAtlas, comprising 12,453 binaries and over 7 million functions for capability evaluation; and BinAres, containing 12,291 binaries and 54 real-world 1-day vulnerabilities for evaluating vulnerability detection performance in practical IoT firmware settings. Using these datasets, we evaluate nine representative BFSD tools, analyze the challenges and limitations of existing BFSD tools, and investigate the consistency among BFSD tools. We also propose an actionable strategy for combining BFSD tools to enhance overall performance (an improvement of 13.4%). Our study not only advances the practical adoption of BFSD tools but also provides valuable resources and insights to guide future research in scalable and automated binary similarity detection.
DOI 原文 ·
@inproceedings{paperbot9301,
title = {A Large Scale Study of AI-based Binary Function Similarity Detection Techniques for Security Researchers and Practitioners},
author = {Jingyi Shi and Yufeng Chen and Yang Xiao and Yuekang Li and Zhengzi Xu and Sihao Qiu and Chi Zhang and Keyu Qi and Yeting Li and Xingchu Chen and Yanyan Zou and Yang Liu and Wei Huo},
booktitle = {ASE},
year = {2025},
doi = {10.1109/ase63991.2025.00093}
}