PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
Synapse
⌘+K
Synapse
June 6, 2026Journal of EngineeringOpen Access

Comparative Evaluation of Supervised Machine Learning Models for IoT Botnet Detection using Random Forest, XGBoost, and ANN

View Full Paper
Ask AI
Bookmark
Share

Authors

ATAli Mohammed Noori Tarab

Discussion

Loading...

Member takes

Overview

Randomized trial compares strength of machine learning models for botnet detection in IoT networks, indicating XGBoost's superiority.

Key Points

  • The aim is to evaluate machine learning models for detecting botnet attacks in IoT networks using the N-BaIoT dataset.
  • Compared three models: Random Forest, XGBoost, and Artificial Neural Network (ANN).
  • Utilized 115 traffic features from N-BaIoT dataset for classification.
  • Evaluated performance metrics including accuracy, precision, recall, F1-score, and inference time.
  • XGBoost achieved 99.12% accuracy, 98.98% precision, and 99.26% recall with an AUC of 0.998.
  • Random Forest had an accuracy of 97.98%, while ANN provided 96.75% accuracy.
  • XGBoost showed the fastest inference time of 0.018 ms per sample, outperforming Random Forest (0.021 ms) and ANN (0.035 ms).

Cite This Study

Ali Mohammed Noori Tarab (2026) studied this question.

synapsesocial.com/papers/6a23b83e71a5da9775e74824https://doi.org/10.31026/j.eng.2026.06.02
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1A Comparative Study of Machine Learning Algorithms for IoT Cybersecurity2025
  2. 2Enhanced Botnet Attack Detection using Machine Learning and Neural Networks2024 · 10 citations
  3. 3Accurate and Efficient Security Authentication of IoT Devices using Machine Learning Algorithms2024 · 2 citations
  4. 4Detection of Various Botnet Attacks Using Machine Learning Techniques2024
  5. 5IoT Botnet Detection: A Comparative Performance Analysis of Various ML Models on IoT-23 Dataset2025