Scholarlink

Network anomaly detection is vital as it offers an efficient tool for identifying and preventing cyberattacks. Many researchers have used various autoencoder-based deep learning techniques to enhance network security against such attacks. This study proposes an optimal autoencoder model for detecting abnormal traffic samples more effectively. The selected latent layer dimension significantly impacts the detection performance in our proposed method. We assessed the effectiveness of our suggested method utilizing the NSL-KDD dataset, using metrics of accuracy, precision, recall, and F1-score.

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

An Efficient Network Anomaly Detection Approach Based on Autoencoder

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Safa Mohamed,
  • Chahira Mahjoub,
  • Ridha Ejbali

摘要

Network anomaly detection is vital as it offers an efficient tool for identifying and preventing cyberattacks. Many researchers have used various autoencoder-based deep learning techniques to enhance network security against such attacks. This study proposes an optimal autoencoder model for detecting abnormal traffic samples more effectively. The selected latent layer dimension significantly impacts the detection performance in our proposed method. We assessed the effectiveness of our suggested method utilizing the NSL-KDD dataset, using metrics of accuracy, precision, recall, and F1-score.