arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2305.09673cs.CRcs.AIcs.LG
收藏

使用两阶段深度学习模型进行漏洞检测

Vulnerability Detection Using Two-Stage Deep Learning Models

Arab International University(阿拉伯国际大学)

Mohamed Mjd Alhafi, Mohammad Hammade, Khloud Al Jallad

AI总结:

针对传统非AI漏洞检测方法假阳性与假阴性率高的问题,提出两阶段深度学习方案,利用CNN和CNN-LTSM模型分别对C/C++源代码进行二分类和多分类漏洞检测,在SySeVR数据集上分别达到99%和98%的准确率。

摘要:

应用程序安全是开发现代软件的重要组成部分,因为许多攻击依赖于软件中的漏洞。由于技术的进步,全球范围内的攻击数量正在增加。公司必须在软件的开发、测试和部署的每个阶段都包含安全性,以防止数据泄露。有几种检测软件漏洞的非AI方法,如静态应用程序安全测试(SAST)和动态应用程序安全测试(DAST)。然而,这些方法具有很高的假阳性率和假阴性率。另一方面,研究人员一直对开发基于AI的漏洞检测系统感兴趣,采用如BERT、BLSTM等深度学习模型。在本文中,我们提出了一个两阶段的解决方案,为C/C++源代码中的漏洞检测提出了两个深度学习模型,第一阶段是CNN,用于检测源代码是否包含任何漏洞(二分类模型),第二阶段是CNN-LTSM,将此漏洞分类为50种不同类型的漏洞类别(多分类模型)。实验在SySeVR数据集上进行。结果显示第一阶段准确率为99%,第二阶段为98%。

英文摘要:

Application security is an essential part of developing modern software, as lots of attacks depend on vulnerabilities in software. The number of attacks is increasing globally due to technological advancements. Companies must include security in every stage of developing, testing, and deploying their software in order to prevent data breaches. There are several methods to detect software vulnerability Non-AI-based such as Static Application Security Testing (SAST) and Dynamic Application Security Testing (DAST). However, these approaches have substantial false-positive and false-negative rates. On the other side, researchers have been interested in developing an AI-based vulnerability detection system employing deep learning models like BERT, BLSTM, etc. In this paper, we proposed a two-stage solution, two deep learning models were proposed for vulnerability detection in C/C++ source codes, the first stage is CNN which detects if the source code contains any vulnerability (binary classification model) and the second stage is CNN-LTSM that classifies this vulnerability into a class of 50 different types of vulnerabilities (multiclass classification model). Experiments were done on SySeVR dataset. Results show an accuracy of 99% for the first and 98% for the second stage.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑