Scholarlink

<p>This study proposes a feature selection technique combined with an Attention-Based Bidirectional Long Short-Term Memory (Abi-LSTM) model for intrusion detection. The approach operates in three stages: pre-processing, feature selection, and classification. Primarily, data is collected and pre-processed, followed by the application of a novel Parrot Optimization Algorithm (POA) to select significant features from each network packet. These selected features are then classified using the Abi-LSTM model to distinguish between normal and intrusive data. The NSL-KDD and UNSW-NB15 datasets were utilized to validate the suggested approach, with accuracy levels of over 98% and 95%, respectively. These results demonstrate superior classification efficiency compared to existing intrusion detection systems.</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

Intelligent intrusion detection system for cloud computing with Parrot optimization and attention-based Bi-LSTM

  • 期刊论文

  • 发表日期：

    2025年12月8日

查看全文
  • Vindhya P. Malagi,
  • Reshma S,
  • Manjunath Ramanna Lamani,
  • Krishna Suresh B V N V,
  • R. Sahana Lokesh

摘要

This study proposes a feature selection technique combined with an Attention-Based Bidirectional Long Short-Term Memory (Abi-LSTM) model for intrusion detection. The approach operates in three stages: pre-processing, feature selection, and classification. Primarily, data is collected and pre-processed, followed by the application of a novel Parrot Optimization Algorithm (POA) to select significant features from each network packet. These selected features are then classified using the Abi-LSTM model to distinguish between normal and intrusive data. The NSL-KDD and UNSW-NB15 datasets were utilized to validate the suggested approach, with accuracy levels of over 98% and 95%, respectively. These results demonstrate superior classification efficiency compared to existing intrusion detection systems.