Scholarlink

The Internet of Things (IoT) infrastructure is an emerging and growing smart business model in day-to-day life in all fields. Security concerns are a big question mark and a challenge in this internet-automated network smart infrastructure because different security vulnerabilities and anomaly attacks are also rising at the same speed. These vulnerability attacks could happen due to various reasons, and they cause failures in IoT network system applications. In the modern world, Machine Learning (ML) models provide various predictive methods, supporting more accurate results for future forecasting to prevent attacks and vulnerabilities. This article compares existing standard ML algorithms to predict the performance and accuracy of different attacks in an IoT network. The consideration and comparison of classical ML models include Logistic Regression (LR), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), and Artificial Neural Network (ANN) using Kaggle platform'sIoT networkdataset. This evaluation provides an accuracy of 99.4% from DT, RF, and ANN. Additionally, RF obtainsanimpactful modelbeyond the selected dataset.

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

Evaluating Classical Machine Learning Models for Predicting Vulnerabilities in IoT Network Datasets

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • S. Poorana Senthilkumar,
  • R. Rajesh Kanna,
  • N. Thangarasu,
  • P. S. Vijayalakshmi,
  • A. Muthusamy,
  • G. D. Praveenkumar

摘要

The Internet of Things (IoT) infrastructure is an emerging and growing smart business model in day-to-day life in all fields. Security concerns are a big question mark and a challenge in this internet-automated network smart infrastructure because different security vulnerabilities and anomaly attacks are also rising at the same speed. These vulnerability attacks could happen due to various reasons, and they cause failures in IoT network system applications. In the modern world, Machine Learning (ML) models provide various predictive methods, supporting more accurate results for future forecasting to prevent attacks and vulnerabilities. This article compares existing standard ML algorithms to predict the performance and accuracy of different attacks in an IoT network. The consideration and comparison of classical ML models include Logistic Regression (LR), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), and Artificial Neural Network (ANN) using Kaggle platform'sIoT networkdataset. This evaluation provides an accuracy of 99.4% from DT, RF, and ANN. Additionally, RF obtainsanimpactful modelbeyond the selected dataset.