Scholarlink

With the exponential increase in transmission of data daily, data has become highly susceptible to security breaches and intrusions. Although a set of rules can help a software navigate through intrusions and alert the networks users, they still struggle with zero-day attacks. This study aims at drawing comparisons between different novel frameworks utilizing various machine learning algorithms as well as contrasting the performance of deep learning algorithms with that of ensemble learning technique. Performance of algorithms such as Long Short-Term Memory (LSTM), Feed-Forward Neural Network (FFNN), and Extreme Gradient Boosting (XGBoost) is explored. Noteworthy results are obtained with LSTM demonstrating 99.9976%, FFNN achieving 99.9731%, and XGBoost showcasing 99.7358% accuracy.

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

A Framework for Intrusion Detection System Using Deep Learning

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Gauri Gera,
  • Supriya Raheja

摘要

With the exponential increase in transmission of data daily, data has become highly susceptible to security breaches and intrusions. Although a set of rules can help a software navigate through intrusions and alert the networks users, they still struggle with zero-day attacks. This study aims at drawing comparisons between different novel frameworks utilizing various machine learning algorithms as well as contrasting the performance of deep learning algorithms with that of ensemble learning technique. Performance of algorithms such as Long Short-Term Memory (LSTM), Feed-Forward Neural Network (FFNN), and Extreme Gradient Boosting (XGBoost) is explored. Noteworthy results are obtained with LSTM demonstrating 99.9976%, FFNN achieving 99.9731%, and XGBoost showcasing 99.7358% accuracy.