Attacks Detection in Internet of Things Using Machine Learning Techniques: A Review

Abstract

The proliferation of IoT devices across sectors such as home automation, business, healthcare, and transportation has led to the generation of vast amounts of sensitive data. This widespread adoption has introduced significant security challenges and vulnerabilities. This study aims to analyze and evaluate machine learning (ML) and deep learning (DL) models for detecting malicious activities in IoT networks, with a focus on improving cybersecurity measures. We conducted a comprehensive review of various ML and DL models, including Random Forest, Decision Tree, HTA-GAN, Hybrid CNN-LSTM, and SVM. The study also includes an evaluation of the datasets used for identifying harmful data, ensuring effective detection of large-scale attacks in IoT ecosystems. Our findings indicate that these models enhance IoT security by deploying efficient intrusion detection systems (IDS) using reliable, large-scale datasets. The study highlights the performance of these models in balancing security and resource management, given the constraints of IoT devices.ML and DL approaches offer significant security benefits for IoT networks, despite the challenges associated with their implementation. The study underscores the importance of future research to address these challenges and further improve IoT security. The results provide valuable insights into the application of ML/DL models in IoT security, contributing to both theoretical knowledge and practical solutions for enhancing cybersecurity in IoT ecosystems.

Keywords

• IoT Devices
• Machine Learning
• Security Attacks
• Deep Learning
• Intrusion Detection Systems