• Dr.Shalini Kumari
• Anand Mohan
• Deepak Kumar
• Rahul Ranjan
• Dr.Gopal Chandra Mahato

The rapid proliferation of Internet of Things (IoT) devices has transformed multiple sectors, from healthcare and agriculture to industrial automation. However, this massive expansion has led to a corresponding increase in vulnerabilities, rendering IoT networks susceptible to various cyber-attacks. Traditional security approaches often fail to meet the needs of IoT due to device heterogeneity, resource constraints, and large-scale deployment. This paper proposes the use of Artificial Intelligence (AI) techniques, particularly machine learning (ML) and deep learning (DL), to enhance network attack detection in IoT systems. A comprehensive survey of existing AI-based attack detection methods is presented, followed by the development of a hybrid model that combines supervised, unsupervised, and deep learning techniques. The proposed model demonstrates an improvement in attack detection accuracy, scalability, and efficiency, while reducing false positives. The study also discusses challenges, potential solutions, and future directions for integrating AI in IoT security.

DL,ML<AI

"A Hybrid AI Approach for Detecting Network Attacks in IoT Environments", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 1, page no.g591-g595, January-2025, Available :http://www.jetir.org/papers/JETIR2501662.pdf

"A Hybrid AI Approach for Detecting Network Attacks in IoT Environments", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 1, page no. ppg591-g595, January-2025, Available at : http://www.jetir.org/papers/JETIR2501662.pdf