AI-Driven IoT Security: Unleashing Machine Learning and Deep Learning for Autonomous Threat Detection and Resilience

Rimlon Shibi S., Thandaiah Prabu R.

2025

Abstract

The rapid growth of the Internet of Things (IoT) has introduced new cybersecurity challenges, as traditional security methods struggle to cope with evolving threats. Machine learning (ML) and deep learning (DL) techniques are emerging as promising solutions to detect and mitigate IoT-related attacks in real-time. This paper reviews the latest research on using ML and DL for IoT attack detection, offering insights into their strengths, weaknesses, and practical applications. IoT networks face a variety of threats, including Distributed Denial of Service (DDoS), botnet attacks, malware, ransomware, and data poisoning. ML models, such as decision trees, random forests, support vector machines, and ensemble methods, are commonly applied to classify malicious behaviors based on network traffic features. In addition, DL models like Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Generative Adversarial Networks (GANs) are gaining popularity for their ability to automatically detect complex attack patterns. Hybrid models, such as CNN-LSTM (Long-Short Term Memory) and federated learning approaches, are explored for their ability to combine the strengths of different architectures while preserving privacy. However, challenges such as computational overhead, adversarial attacks, real-time implementation, and explainability of AI models remain significant barriers. Future research should focus on developing lightweight, adversarial-resilient models, improving explainability through eXplainable AI (XAI) techniques, and integrating block chain and federated learning to enhance the security and scalability of IoT networks. This paper aims to highlight the potential of AI-driven solutions in safeguarding IoT environments while addressing existing limitations.

Paper Citation

in Harvard Style

S. R. and R. T. (2025). AI-Driven IoT Security: Unleashing Machine Learning and Deep Learning for Autonomous Threat Detection and Resilience. In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25; ISBN 978-989-758-777-1, SciTePress, pages 343-350. DOI: 10.5220/0013929700004919

in Bibtex Style

@conference{icrdicct`2525,
author={Rimlon S. and Thandaiah R.},
title={AI-Driven IoT Security: Unleashing Machine Learning and Deep Learning for Autonomous Threat Detection and Resilience},
booktitle={Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25},
year={2025},
pages={343-350},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013929700004919},
isbn={978-989-758-777-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25
TI - AI-Driven IoT Security: Unleashing Machine Learning and Deep Learning for Autonomous Threat Detection and Resilience
SN - 978-989-758-777-1
AU - S. R.
AU - R. T.
PY - 2025
SP - 343
EP - 350
DO - 10.5220/0013929700004919
PB - SciTePress