Scholarlink

This paper proposed a deep learning (DL) based Hidden Naïve Bayes (HNB) method that uses a 12-layer Convolutional Neural Network (CNN) model as a hidden layer before the Gaussian Naïve Bayes (GNB) classifier to extract features from the MTA-KDD’19 dataset and divide MTA-KDD’19 into two categories: malware and regular. The system uses recall, F1-score, precision, and accuracy as performance metrics. Tests indicate that the suggested Hidden Naïve Bayes performs well in detecting malware.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Suggested Hidden Naïve Bayesian Method based on Deep Learning for Malware Detection

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Shaymaa A. kadhom,
  • Ali N. Kareem

摘要

This paper proposed a deep learning (DL) based Hidden Naïve Bayes (HNB) method that uses a 12-layer Convolutional Neural Network (CNN) model as a hidden layer before the Gaussian Naïve Bayes (GNB) classifier to extract features from the MTA-KDD’19 dataset and divide MTA-KDD’19 into two categories: malware and regular. The system uses recall, F1-score, precision, and accuracy as performance metrics. Tests indicate that the suggested Hidden Naïve Bayes performs well in detecting malware.