Scholarlink

This research evaluates intrusion detection systems for SCADA and Industrial Control Systems (ICS) networks, critically analyzing machine learning, deep learning, and traditional algorithms’ effectiveness in cybersecurity. By examining multiple datasets and performance metrics, the study identifies the most promising intrusion detection approaches for protecting critical infrastructure. The research highlights hybrid and deep learning algorithms as the most effective, with top-performing methods like Res-TranBiLSTM, Hybrid Ensemble Learning, and LTH-CNN demonstrating detection accuracies exceeding 97% and minimal false alarm rates.

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 in Industrial Control Systems: A Comprehensive Evaluation of Machine Learning and Deep Learning Approaches

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Esther Dhiramo,
  • Ali Al-Sinayyid,
  • Austin Higginbotham,
  • Joseph Sanchez,
  • Joshua Gilliland,
  • Samuel Adewumi

摘要

This research evaluates intrusion detection systems for SCADA and Industrial Control Systems (ICS) networks, critically analyzing machine learning, deep learning, and traditional algorithms’ effectiveness in cybersecurity. By examining multiple datasets and performance metrics, the study identifies the most promising intrusion detection approaches for protecting critical infrastructure. The research highlights hybrid and deep learning algorithms as the most effective, with top-performing methods like Res-TranBiLSTM, Hybrid Ensemble Learning, and LTH-CNN demonstrating detection accuracies exceeding 97% and minimal false alarm rates.