Scholarlink

<p>The proposed scheme in the paper focuses on the stacked hybrid deep learning model, which includes LSTM (long-short term memory), GRU (gated recurrent unit), SimpleRNN (recurrent neural network), and CNN (convolutional neural network) architectures for enhancing intrusion detection in IoT (Internet of Things) gateway management systems. This work leverages these neural networks in a union to learn both temporal and spatial features from network traffic that enable the model actually to detect complex cyber threats. The model produced showed good performance, with 99.9% in training accuracy, 99.84% in testing, and effective precision, recall, and F1-score. Its robustness was further evaluated against some of the state-of-the-art approaches. Noteworthy improvements included all major evaluation metrics like MCC (Matthews correlation coefficient), MSE (Mean square error), and AUC (Area under curve). Moreover, comparative analysis of the proposed model has been done with latest state of art work on the basis of metrics like precision, recall, F1 score and accuracy. The results confirm the model has a high potential for improving security in both IoT and WSN (wireless sensor network) environments. Therefore, it will be very effective in real-world intrusion detection.</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

Enhancing IoT gateway management security: a deep learning based framework for intrusion detection and threat mitigation

  • 期刊论文

  • 发表日期：

    2025年3月11日

查看全文
  • Sonal,
  • Suman Deswal

摘要

The proposed scheme in the paper focuses on the stacked hybrid deep learning model, which includes LSTM (long-short term memory), GRU (gated recurrent unit), SimpleRNN (recurrent neural network), and CNN (convolutional neural network) architectures for enhancing intrusion detection in IoT (Internet of Things) gateway management systems. This work leverages these neural networks in a union to learn both temporal and spatial features from network traffic that enable the model actually to detect complex cyber threats. The model produced showed good performance, with 99.9% in training accuracy, 99.84% in testing, and effective precision, recall, and F1-score. Its robustness was further evaluated against some of the state-of-the-art approaches. Noteworthy improvements included all major evaluation metrics like MCC (Matthews correlation coefficient), MSE (Mean square error), and AUC (Area under curve). Moreover, comparative analysis of the proposed model has been done with latest state of art work on the basis of metrics like precision, recall, F1 score and accuracy. The results confirm the model has a high potential for improving security in both IoT and WSN (wireless sensor network) environments. Therefore, it will be very effective in real-world intrusion detection.