首页> 外文OA文献 >Mal-Netminer: Malware Classification Approach based on Social Network Analysis of System Call Graph
【2h】

Mal-Netminer: Malware Classification Approach based on Social Network Analysis of System Call Graph

机译:mal-Netminer:基于社交网络的恶意软件分类方法   系统调用图分析

代理获取
本网站仅为用户提供外文OA文献查询和代理获取服务,本网站没有原文。下单后我们将采用程序或人工为您竭诚获取高质量的原文,但由于OA文献来源多样且变更频繁,仍可能出现获取不到、文献不完整或与标题不符等情况,如果获取不到我们将提供退款服务。请知悉。

摘要

As the security landscape evolves over time, where thousands of species ofmalicious codes are seen every day, antivirus vendors strive to detect andclassify malware families for efficient and effective responses against malwarecampaigns. To enrich this effort, and by capitalizing on ideas from the socialnetwork analysis domain, we build a tool that can help classify malwarefamilies using features driven from the graph structure of their system calls.To achieve that, we first construct a system call graph that consists of systemcalls found in the execution of the individual malware families. To exploredistinguishing features of various malware species, we study social networkproperties as applied to the call graph, including the degree distribution,degree centrality, average distance, clustering coefficient, network density,and component ratio. We utilize features driven from those properties to builda classifier for malware families. Our experimental results show thatinfluence-based graph metrics such as the degree centrality are effective forclassifying malware, whereas the general structural metrics of malware are lesseffective for classifying malware. Our experiments demonstrate that theproposed system performs well in detecting and classifying malware familieswithin each malware class with accuracy greater than 96%.
机译:随着安全形势的发展,每天都会看到成千上万种恶意代码,防病毒供应商努力检测并分类恶意软件家族,以对恶意软件活动做出有效响应。为了丰富这项工作,并利用社交网络分析领域的思想,我们构建了一个工具,该工具可以使用由其系统调用的图结构驱动的功能来帮助对恶意软件家族进行分类。为此,我们首先构建一个包含以下内容的系统调用图:在执行单个恶意软件系列时发现的系统调用数量。为了探索各种恶意软件种类的区别特征,我们研究了应用于调用图的社交网络属性,包括程度分布,程度中心性,平均距离,聚类系数,网络密度和组件比率。我们利用这些属性驱动的功能来构建恶意软件家族的分类器。我们的实验结果表明,基于影响度的图形指标(例如中心度)可有效地对恶意软件进行分类,而恶意软件的一般结构指标对恶意软件进行分类的效果较差。我们的实验表明,所提出的系统在检测和分类每个恶意软件类别中的恶意软件家族方面表现良好,准确度大于96%。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
代理获取

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号