Scholarlink

In this paper, we propose a deep learning neural network (DNN) using the Auto encoder model for the intrusion detection. An important component of any internet-connected device is a Network Intrusion Detection System (NIDS). NIDS detects network-based attacks, such as Denial of Service (DoS) attacks as the focus of this research. We identified and analyzed the Auto encoder for measuring its accuracy, precision, recall and F-measure and thus achieved a 99% hit / success rate. To evaluate the performance, we utilized the network intrusion dataset Network Security Laboratory-Knowledge Discovery in Databases (NSLKDD).

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

Denial of Service (DoS) Attack Detection Using Autoencoder-Based Deep Learning and Machine Learning Techniques

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Mohammad Imtiyaz Gulbarga,
  • A. I. Khan,
  • Remudin Reshid Mekuria,
  • Mekia Shigute Gaso,
  • Nazira Abdillaeva

摘要

In this paper, we propose a deep learning neural network (DNN) using the Auto encoder model for the intrusion detection. An important component of any internet-connected device is a Network Intrusion Detection System (NIDS). NIDS detects network-based attacks, such as Denial of Service (DoS) attacks as the focus of this research. We identified and analyzed the Auto encoder for measuring its accuracy, precision, recall and F-measure and thus achieved a 99% hit / success rate. To evaluate the performance, we utilized the network intrusion dataset Network Security Laboratory-Knowledge Discovery in Databases (NSLKDD).