一句话：提出αDiff，使用深度神经网络检测跨版本二进制代码相似性，减少对专家句法特征的依赖。
二进制代码相似性检测可用于补丁分析、抄袭检测、恶意软件检测和漏洞搜索等。现有方案通常依赖专家知识，从二进制代码中提取特定句法特征再进行比较，存在性能开销高或检测精度低的问题；同时，少有方案适合检测跨版本二进制代码的相似性，因为跨版本二进制不仅在句法结构上可能不同，在语义上也会有轻微差异。αDiff 针对这些问题，采用深度神经网络（DNN）进行跨版本二进制代码相似性检测，以 DNN 作为检测方法。摘要未给出具体模型结构、训练数据与实验指标。
Binary code similarity detection (BCSD) has many applications, including patch analysis, plagiarism detection, malware detection, and vulnerability search etc. Existing solutions usually perform comparisons over specific syntactic features extracted from binary code, based on expert knowledge. They have either high performance overheads or low detection accuracy. Moreover, few solutions are suitable for detecting similarities between cross-version binaries, which may not only diverge in syntactic structures but also diverge slightly in semantics.
DOI 原文 ·
@inproceedings{paperbot4708,
title = {αDiff: cross-version binary code similarity detection with DNN},
author = {Bingchang Liu and Wei Huo and Chao Zhang and Wenchao Li and Feng Li and Aihua Piao and Wei Zou},
booktitle = {ASE},
year = {2018},
doi = {10.1145/3238147.3238199}
}