返回
Unveiling malicious PDF behavior: Interpretable classification and profiling malicious PDF using TabNet
DOI:10.1016/j.jisa.2026.104487.png)
摘要
En 中文
• 使用TabNet进行恶意PDF检测,在提供高检测性能的同时保证可解释性。• 利用TabNet的动态注意力机制识别分类相关的特征,减少特征工程。• 对TabNet的可解释性进行全面分析,为局部和全局特征重要性提供见解。• 在真实世界的CIC-Evasive-PDFMal2022数据集上达到当前最佳结果。
Keyword:
Malicious PDF detection
TabNet
Interpretability
Feature importance
Machine learning
期刊
IF:
3.7
论文数:
1.9K
被引数:
4.9K
机构
引用论文
A sequential deep learning framework for a robust and resilient network intrusion detection system
COMPUTERS & SECURITY
IF5.4
Taking the Human Out of the Loop: A Review of Bayesian Optimization将人类带出循环: 贝叶斯优化的回顾
PROCEEDINGS OF THE IEEE
IF25.9
DarknetSec: A novel self-attentive deep learning method for darknet traffic classification and application identification
COMPUTERS & SECURITY
IF5.4
HAE-HRL: A network intrusion detection system utilizing a novel autoencoder and a hybrid enhanced LSTM-CNN-based residual networkHAE-HRL:一种利用新型自动编码器和基于混合增强LSTM-CNN残差网络的网络入侵检测系统
COMPUTERS & SECURITY
IF5.4

