Scholarlink

This literature review evaluates the effectiveness of various machine learning (ML) and deep learning (DL) algorithms in detecting and preventing IoT cyber threats. Performance metrics such as accuracy and F1-score are compared for traditional ML models (e.g., K-Nearest Neighbors, Support Vector Machine), ensemble methods (e.g., Random Forest, AdaBoost), and deep learning architectures (e.g., Long Short-Term Memory, Convolutional Neural Network, Multi-Layer Perceptron). The study highlights that ensemble methods, particularly Random Forest, achieve high accuracy and F1-scores, making them effective in many scenarios. Deep learning models show strong performance but require more computational resources. This review provides a comprehensive comparison to guide the development of more secure IoT systems.

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

Comparing Machine Learning Algorithms for Detection and Prevention of Cyber-Attacks on IoT Devices: A Literature Review

  • 章节

  • 发表日期：

    2026年

查看全文
  • Joshua Gilliland,
  • Ali Al-Sinayyid,
  • Renata Castellanos,
  • Natwange Chiwele,
  • Esther Dhiramo,
  • Austin Higginbotham,
  • Elías Valencia

摘要

This literature review evaluates the effectiveness of various machine learning (ML) and deep learning (DL) algorithms in detecting and preventing IoT cyber threats. Performance metrics such as accuracy and F1-score are compared for traditional ML models (e.g., K-Nearest Neighbors, Support Vector Machine), ensemble methods (e.g., Random Forest, AdaBoost), and deep learning architectures (e.g., Long Short-Term Memory, Convolutional Neural Network, Multi-Layer Perceptron). The study highlights that ensemble methods, particularly Random Forest, achieve high accuracy and F1-scores, making them effective in many scenarios. Deep learning models show strong performance but require more computational resources. This review provides a comprehensive comparison to guide the development of more secure IoT systems.