当前位置: X-MOL 学术arXiv.cs.CR › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
ThreatZoom: CVE2CWE using Hierarchical Neural Network
arXiv - CS - Cryptography and Security Pub Date : 2020-09-24 , DOI: arxiv-2009.11501
Ehsan Aghaei, Waseem Shadid, Ehab Al-Shaer

The Common Vulnerabilities and Exposures (CVE) represent standard means for sharing publicly known information security vulnerabilities. One or more CVEs are grouped into the Common Weakness Enumeration (CWE) classes for the purpose of understanding the software or configuration flaws and potential impacts enabled by these vulnerabilities and identifying means to detect or prevent exploitation. As the CVE-to-CWE classification is mostly performed manually by domain experts, thousands of critical and new CVEs remain unclassified, yet they are unpatchable. This significantly limits the utility of CVEs and slows down proactive threat mitigation. This paper presents the first automatic tool to classify CVEs to CWEs. ThreatZoom uses a novel learning algorithm that employs an adaptive hierarchical neural network which adjusts its weights based on text analytic scores and classification errors. It automatically estimates the CWE classes corresponding to a CVE instance using both statistical and semantic features extracted from the description of a CVE. This tool is rigorously tested by various datasets provided by MITRE and the National Vulnerability Database (NVD). The accuracy of classifying CVE instances to their correct CWE classes are 92% (fine-grain) and 94% (coarse-grain) for NVD dataset, and 75% (fine-grain) and 90% (coarse-grain) for MITRE dataset, despite the small corpus.

中文翻译:

ThreatZoom:使用分层神经网络的 CVE2CWE

Common Vulnerabilities and Exposures (CVE) 代表了共享已知信息安全漏洞的标准方法。一个或多个 CVE 被分组到通用弱点枚举 (CWE) 类中,目的是了解这些漏洞导致的软件或配置缺陷和潜在影响,并确定检测或防止漏洞利用的方法。由于 CVE 到 CWE 的分类主要由领域专家手动执行,因此数千个关键的和新的 CVE 仍未分类,但它们是不可修补的。这极大地限制了 CVE 的效用并减慢了主动威胁缓解的速度。本文介绍了第一个将 CVE 分类为 CWE 的自动工具。ThreatZoom 使用一种新颖的学习算法,该算法采用自适应分层神经网络,可根据文本分析分数和分类错误调整其权重。它使用从 CVE 的描述中提取的统计和语义特征自动估计与 CVE 实例对应的 CWE 类。该工具经过 MITRE 和国家漏洞数据库 (NVD) 提供的各种数据集的严格测试。将 CVE 实例分类为正确的 CWE 类的准确率对于 NVD 数据集为 92%(细粒度)和 94%(粗粒度),对于 MITRE 数据集为 75%(细粒度)和 90%(粗粒度) ,尽管语料库很小。它使用从 CVE 的描述中提取的统计和语义特征自动估计与 CVE 实例对应的 CWE 类。该工具经过 MITRE 和国家漏洞数据库 (NVD) 提供的各种数据集的严格测试。将 CVE 实例分类为正确的 CWE 类的准确率对于 NVD 数据集为 92%(细粒度)和 94%(粗粒度),对于 MITRE 数据集为 75%(细粒度)和 90%(粗粒度) ,尽管语料库很小。它使用从 CVE 的描述中提取的统计和语义特征自动估计与 CVE 实例对应的 CWE 类。该工具经过 MITRE 和国家漏洞数据库 (NVD) 提供的各种数据集的严格测试。将 CVE 实例分类为正确的 CWE 类的准确率对于 NVD 数据集为 92%(细粒度)和 94%(粗粒度),对于 MITRE 数据集为 75%(细粒度)和 90%(粗粒度) ,尽管语料库很小。
更新日期:2020-09-25
down
wechat
bug