.png){kind=icon}
返回
Explainable android malware detection and malicious code localization using graph attention
.png){kind=icon}
PRE
AI
DOI：10.1016/j.jisa.2026.104385.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
• Proposes a novel approach for automatic malicious code localization at both class and fine-grained method levels. • Integrates Graph Neural Networks and attention mechanisms to provide interpretable and explainable malware analysis. • Demonstrates robustness by evaluating on both synthetic and real-world malware datasets. • Significantly reduces manual analysis effort by automating the identification of malicious code segments. • Achieves a high recall rate of 97.27% and an F1-score of 95.30% at class-level and 96.02% recall with an F1-score of 92.68% at method-level localization.
Keyword:
malicious code localization
graph neural networks
attention mechanisms
android malware detection
explainable ai
期刊
IF:
3.7
论文数:
1.9K
被引数:
4.9K
机构
引用论文
A Combination Method for Android Malware Detection Based on Control Flow Graphs and Machine Learning Algorithms.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏DMalNet: Dynamic malware analysis based on API feature engineering and graph learningDMalNet: 基于API特征工程和图学习的动态恶意软件分析COMPUTERS & SECURITY
COMPUTERS & SECURITYIF5.4
PREAI
分享收藏A novel Android malware detection method with API semantics extraction一种基于API语义提取的Android恶意软件检测方法COMPUTERS & SECURITY
COMPUTERS & SECURITYIF5.4
PREAI
分享收藏
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SeGDroid: An Android malware detection method based on sensitive function call graph learningSeGDroid: 一种基于敏感函数调用图学习的Android恶意软件检测方法
PREAI
分享收藏A multi-view context-aware approach to Android malware detection and malicious code localization一种多视图上下文感知的Android恶意软件检测和恶意代码定位方法OAAI
OAAI分享收藏
查看更多内容