Scholarlink

<p>The rapidly expanding Internet of Things (IoT) sector plays a pivotal role in improving various aspects of daily life, particularly in healthcare and industrial applications, where secure, real-time data collection and communication are essential. However, the increasing number of interconnected devices, often constrained by limited processing power, introduces significant security vulnerabilities that can be exploited by malicious actors. Traditional security mechanisms, such as firewalls and antivirus software, are insufficient in addressing the unique challenges posed by IoT environments. A promising solution to this problem is the integration of machine learning (ML) techniques to enhance attack detection capabilities. Specifically, ML can significantly advance Network Intrusion Detection Systems (NIDS) by providing adaptive and intelligent threat detection. To address these challenges and fully leverage the potential of ML in IoT security, this paper proposes a novel NIDS architecture based on the deep learning model Convolutional Neural Network (CNN). The proposed system is specifically designed to detect and mitigate security threats within IoT environments. Trained using the CICIoT2023, Edge-IIoTset, and CICIoMT2024 datasets, the model achieves high accuracy, flexibility, and lower latency in both binary and multi-class classification tasks. Experimental results demonstrate that the proposed NIDS outperforms state-of-the-art solutions across all key evaluation metrics including accuracy, precision, recall, and f1-score, thereby providing a robust and effective real-time security defense mechanism for IoT networks.</p>

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

Network Intrusion Detection System Using Convolutional Neural Networks: NIDS-DL-CNN for IoT Security

  • 期刊论文

  • 发表日期：

    2025年2月25日

查看全文
  • Kamir Kharoubi,
  • Sarra Cherbal,
  • Djamila Mechta,
  • Amjad Gawanmeh

摘要

The rapidly expanding Internet of Things (IoT) sector plays a pivotal role in improving various aspects of daily life, particularly in healthcare and industrial applications, where secure, real-time data collection and communication are essential. However, the increasing number of interconnected devices, often constrained by limited processing power, introduces significant security vulnerabilities that can be exploited by malicious actors. Traditional security mechanisms, such as firewalls and antivirus software, are insufficient in addressing the unique challenges posed by IoT environments. A promising solution to this problem is the integration of machine learning (ML) techniques to enhance attack detection capabilities. Specifically, ML can significantly advance Network Intrusion Detection Systems (NIDS) by providing adaptive and intelligent threat detection. To address these challenges and fully leverage the potential of ML in IoT security, this paper proposes a novel NIDS architecture based on the deep learning model Convolutional Neural Network (CNN). The proposed system is specifically designed to detect and mitigate security threats within IoT environments. Trained using the CICIoT2023, Edge-IIoTset, and CICIoMT2024 datasets, the model achieves high accuracy, flexibility, and lower latency in both binary and multi-class classification tasks. Experimental results demonstrate that the proposed NIDS outperforms state-of-the-art solutions across all key evaluation metrics including accuracy, precision, recall, and f1-score, thereby providing a robust and effective real-time security defense mechanism for IoT networks.