Scholarlink

This study examines the effects of several hyper-parameters, such as the number of epochs, batch size, number of layers and neurons, optimization technique, dropout rate, type of activation function, and learning rate, on deep learning-based static malware detection. To determine the ideal hyper-parameters for our deep learning model, we used the inception approach. Our research shows that convolutional neural networks with inception are more effective than other techniques, and that the correctness of the model is greatly influenced by the choice of hyper-parameter values. In particular, our method causes the neural network model’s accuracy for static malware detection on the Ember dataset to significantly increase (from 84.19% to 90.78%). These findings support the efficacy of our suggested methodology and have significant ramifications for the static malware detection community.

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

Optimized Deep Learning Technique for the Effective Detection of Windows PE Malware

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Kirubavathi Ganapathiyappan,
  • Abhishek Yadav

摘要

This study examines the effects of several hyper-parameters, such as the number of epochs, batch size, number of layers and neurons, optimization technique, dropout rate, type of activation function, and learning rate, on deep learning-based static malware detection. To determine the ideal hyper-parameters for our deep learning model, we used the inception approach. Our research shows that convolutional neural networks with inception are more effective than other techniques, and that the correctness of the model is greatly influenced by the choice of hyper-parameter values. In particular, our method causes the neural network model’s accuracy for static malware detection on the Ember dataset to significantly increase (from 84.19% to 90.78%). These findings support the efficacy of our suggested methodology and have significant ramifications for the static malware detection community.