.png){kind=icon}
返回
Evaluating Dynamic Analysis Features for Android Malware Categorization
.png){kind=icon}
PRE
AI
DOI：10.1109/IWCMC55113.2022.9824225.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Tremendous increase and sophistication in Android applications is making malware detection a challenging task. The use of obfuscation has complicated the task of malware detection, as static analysis can be deceived by different obfuscation schemes. Recently, studies have focused on dynamic analysis of applications, as it is more resilient against obfuscation techniques. CCCS-CIC-AndMal-2020; published by Canadian institute for cybersecurity is a recent data set of extracted features of malicious Android applications. The dynamic features in this data set belong to six categories: memory, network, battery, logs, process and APIs. Previous studies have focused on classification of Android malware using dynamic features. However, the impact of individual categories of dynamic features for malware categorization has not been analyzed in length. In this study, a comprehensive analysis on the impact of all dynamic analysis categories and features on Android malware detection is conducted using different filter and wrapper methods. The most significant categories of dynamic features are reported and important features in those categories are also listed.
Keyword:
Android malware
Dynamic analysis
Feature selection
Classification
期刊
I
IF:
0
论文数:
16
被引数:
0
机构
暂无机构信息
引用论文
KronoDroid: Time-based Hybrid-featured Dataset for Effective Android Malware Detection and CharacterizationKronoDroid: 基于时间的混合特征数据集，用于有效的Android恶意软件检测和表征.png)
COMPUTERS & SECURITY
OAAI
COMPUTERS & SECURITYIF5.4
OAAI分享收藏Research on unsupervised feature learning for Android malware detection based on Restricted Boltzmann Machines基于受限玻尔兹曼机的Android恶意软件无监督特征学习研究OAAI
OAAI分享收藏GDroid: Android malware detection and classification with graph convolutional networkGDroid: 使用图卷积网络进行Android恶意软件检测和分类COMPUTERS & SECURITY
COMPUTERS & SECURITYIF5.4
PREAI
分享收藏Android malware obfuscation variants detection method based on multi-granularity opcode features基于多粒度操作码特征的Android恶意代码混淆变种检测方法
PREAI
分享收藏
查看更多内容