Scholarlink

Network intrusion detection plays a crucial role in safeguarding computer systems and networks against malicious activities. With the increasing complexity and sophistication of cyber threats, there is a growing demand for advanced intrusion detection systems capable of effectively identifying and mitigating various forms of attacks. In this paper, the Bidirectional Modified Gated Recurrent Unit (M-GRU) with Attention Mechanism is another variant of the original GRU architecture that has been modified to improve its performance in classifying network intrusions. It combines the benefits of bidirectional processing, modified GRU cells, and attention mechanisms for enhanced performance. In experiments, the M-GRU with attention mechanism has shown improved performance over AI models for network intrusion classification.

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

Deep Learning for Network Intrusion Detection: Attention-Based Bidirectional Modified Gated Recurrent Unit

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • M. Karthigha,
  • L. Latha,
  • K. Sripriyan

摘要

Network intrusion detection plays a crucial role in safeguarding computer systems and networks against malicious activities. With the increasing complexity and sophistication of cyber threats, there is a growing demand for advanced intrusion detection systems capable of effectively identifying and mitigating various forms of attacks. In this paper, the Bidirectional Modified Gated Recurrent Unit (M-GRU) with Attention Mechanism is another variant of the original GRU architecture that has been modified to improve its performance in classifying network intrusions. It combines the benefits of bidirectional processing, modified GRU cells, and attention mechanisms for enhanced performance. In experiments, the M-GRU with attention mechanism has shown improved performance over AI models for network intrusion classification.