不同编译形式函数的相似回归及对偶控制流图的神经关注

IF 1.5 4区计算机科学 Q4 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Journal Pub Date : 2023-10-11 DOI:10.1093/comjnl/bxad095

Yun Zhang, Yuling Liu, Ge Cheng, Jie Wang

{"title":"不同编译形式函数的相似回归及对偶控制流图的神经关注","authors":"Yun Zhang, Yuling Liu, Ge Cheng, Jie Wang","doi":"10.1093/comjnl/bxad095","DOIUrl":null,"url":null,"abstract":"Abstract Detecting if two functions in different compiled forms are similar has a wide range of applications in software security. We present a method that leverages both semantic and structural features of functions, learned by a neural-net model on the underlying control-flow graphs (CFGs). In particular, we devise a neural function-similarity regressor (NFSR) with attentions on dual CFGs. We train and evaluate NFSR on a dataset consisting of nearly 4 million functions from over 14 900 binary files. Experiments show that NFSR is superior to the SOTA models of SAFE, Gemini and GMN, especially for binary functions with large CFGs. An ablation study shows that attention on dual CFGs plays a significant role in detecting function similarities.","PeriodicalId":50641,"journal":{"name":"Computer Journal","volume":"5 1","pages":"0"},"PeriodicalIF":1.5000,"publicationDate":"2023-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Similarity Regression Of Functions In Different Compiled Forms With Neural Attentions On Dual Control-Flow Graphs\",\"authors\":\"Yun Zhang, Yuling Liu, Ge Cheng, Jie Wang\",\"doi\":\"10.1093/comjnl/bxad095\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract Detecting if two functions in different compiled forms are similar has a wide range of applications in software security. We present a method that leverages both semantic and structural features of functions, learned by a neural-net model on the underlying control-flow graphs (CFGs). In particular, we devise a neural function-similarity regressor (NFSR) with attentions on dual CFGs. We train and evaluate NFSR on a dataset consisting of nearly 4 million functions from over 14 900 binary files. Experiments show that NFSR is superior to the SOTA models of SAFE, Gemini and GMN, especially for binary functions with large CFGs. An ablation study shows that attention on dual CFGs plays a significant role in detecting function similarities.\",\"PeriodicalId\":50641,\"journal\":{\"name\":\"Computer Journal\",\"volume\":\"5 1\",\"pages\":\"0\"},\"PeriodicalIF\":1.5000,\"publicationDate\":\"2023-10-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computer Journal\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1093/comjnl/bxad095\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"COMPUTER SCIENCE, HARDWARE & ARCHITECTURE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer Journal","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1093/comjnl/bxad095","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"COMPUTER SCIENCE, HARDWARE & ARCHITECTURE","Score":null,"Total":0}

引用次数: 0

摘要

摘要检测不同编译形式的两个函数是否相似在软件安全中有着广泛的应用。我们提出了一种利用函数的语义和结构特征的方法，通过在底层控制流图(cfg)上的神经网络模型学习。特别地，我们设计了一个神经功能相似回归器(NFSR)，关注双CFGs。我们在一个数据集上训练和评估NFSR，该数据集由来自14900多个二进制文件的近400万个函数组成。实验表明，NFSR模型优于SAFE、Gemini和GMN的SOTA模型，特别是对于具有较大CFGs的二元函数。一项消融研究表明，对双CFGs的关注在检测功能相似性方面起着重要作用。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Similarity Regression Of Functions In Different Compiled Forms With Neural Attentions On Dual Control-Flow Graphs

Abstract Detecting if two functions in different compiled forms are similar has a wide range of applications in software security. We present a method that leverages both semantic and structural features of functions, learned by a neural-net model on the underlying control-flow graphs (CFGs). In particular, we devise a neural function-similarity regressor (NFSR) with attentions on dual CFGs. We train and evaluate NFSR on a dataset consisting of nearly 4 million functions from over 14 900 binary files. Experiments show that NFSR is superior to the SOTA models of SAFE, Gemini and GMN, especially for binary functions with large CFGs. An ablation study shows that attention on dual CFGs plays a significant role in detecting function similarities.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Computer Journal 工程技术-计算机：软件工程

CiteScore

3.60

自引率

7.10%

发文量

164

审稿时长

4.8 months

期刊介绍： The Computer Journal is one of the longest-established journals serving all branches of the academic computer science community. It is currently published in four sections.