Scholarlink

Intrusion Detection Systems (IDS) have been instrumental in preventing emerging threats from compromising a network. One of the key challenges in the field is to design an IDS with high detection coverage and low false positives. This study investigates the potential of hybrid deep learning systems to address this challenge. We developed a CNN+LSTM model that leverages the spatial feature extraction power of CNN and the temporal sequence learning capacity of LSTM. Experimental results demonstrate that the proposed CNN-LSTM model consistently outperforms LightGBM and XGBoost, achieving the highest accuracy (92.7%), precision (89.5%), recall (81.8%), and F1-score (84.3%), thereby confirming its robustness and effectiveness for intrusion detection. Additionally, comprehensive assessments indicate that for more complex and hidden attack patterns, the CNN+LSTM model is more advanced in terms of detection availability and effectiveness. The relevance of this work emphasises the need to modernise IDS systems by using hybrid deep learning techniques. Furthermore, the combination of convolutional neural networks with LSTM improves detection capacity and supports feature-level detail for new hazards.

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 Intrusion Detection with Hybrid Deep Learning (CNN-LSTM) and Tree-Based Models with XGBoost, and LightGBM

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Jaimin Dave,
  • Chintan Shah,
  • Premal Patel

摘要

Intrusion Detection Systems (IDS) have been instrumental in preventing emerging threats from compromising a network. One of the key challenges in the field is to design an IDS with high detection coverage and low false positives. This study investigates the potential of hybrid deep learning systems to address this challenge. We developed a CNN+LSTM model that leverages the spatial feature extraction power of CNN and the temporal sequence learning capacity of LSTM. Experimental results demonstrate that the proposed CNN-LSTM model consistently outperforms LightGBM and XGBoost, achieving the highest accuracy (92.7%), precision (89.5%), recall (81.8%), and F1-score (84.3%), thereby confirming its robustness and effectiveness for intrusion detection. Additionally, comprehensive assessments indicate that for more complex and hidden attack patterns, the CNN+LSTM model is more advanced in terms of detection availability and effectiveness. The relevance of this work emphasises the need to modernise IDS systems by using hybrid deep learning techniques. Furthermore, the combination of convolutional neural networks with LSTM improves detection capacity and supports feature-level detail for new hazards.