Scholarlink

This paper examines the security challenges posed by the rapid growth of the Internet of Things in sectors such as industrial, health, and agriculture. As IoT systems become more widespread, cyberattacks increasingly threatened them. To address these security issues, we conducted a review of 10 papers on different intrusion detection systems for the Internet of Things. The goal was to see how well they work. In addition, to discover ways of improvement. We show that deep learning-based intrusion detection systems could improve the way we detect online attacks. Especially when using neural networks, these systems can better detect and respond to malicious activity. The combination of machine learning and intrusion detection systems appears to have the potential to improve the security of Internet of Things networks, providing stronger protection against cyberattacks. This is where convolutional neural networks come in. Especially when tested with different datasets, this deep learning model showed very high accuracy in protecting Internet of Things networks. This highlights the importance of using sophisticated algorithms to meet the growing challenges of cyber threats against IoT systems.

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

Evaluating Deep Learning Approaches for Intrusion Detection in IoT Networks

  • 章节

  • 发表日期：

    2026年

查看全文
  • Abdeslem Blali,
  • Souhayla Dargaoui,
  • Mourade Azrour,
  • Azidine Guezzaz,
  • Abdulatif Alabdulatif

摘要

This paper examines the security challenges posed by the rapid growth of the Internet of Things in sectors such as industrial, health, and agriculture. As IoT systems become more widespread, cyberattacks increasingly threatened them. To address these security issues, we conducted a review of 10 papers on different intrusion detection systems for the Internet of Things. The goal was to see how well they work. In addition, to discover ways of improvement. We show that deep learning-based intrusion detection systems could improve the way we detect online attacks. Especially when using neural networks, these systems can better detect and respond to malicious activity. The combination of machine learning and intrusion detection systems appears to have the potential to improve the security of Internet of Things networks, providing stronger protection against cyberattacks. This is where convolutional neural networks come in. Especially when tested with different datasets, this deep learning model showed very high accuracy in protecting Internet of Things networks. This highlights the importance of using sophisticated algorithms to meet the growing challenges of cyber threats against IoT systems.