AI-Powered Anomaly Detection to Strengthen Internet of Things Security and Forestall Cyber Attacks in Networked Device Environments
Sudha Varalakshmi, Suresh Kottur, R. Sasikumar, K. Saravanan, Tanaya Kanungo, Balamurugan Annamalai · 2025
As millions of devices are linked, the IoT has revolutionized numerous businesses by automating and data-driven decision-making. Due to the proliferation of linked devices, cybercriminals target IoT environments for security breaches. This research examines AI-powered anomaly detection systems for real-time threat discovery and mitigation in IoT security. Advanced machine learning and deep learning models based on artificial intelligence can detect suspicious activity in networked environments and early security breaches. Artificial intelligence systems learn from network traffic and device behaviors to respond to emerging cyber threats, unlike rule-based security solutions. The study found that AI-driven anomaly detection can prevent data breaches, malware outbreaks, and DDoS attacks. This study compares artificial intelligence algorithms for real-time anomaly detection across IoT frameworks. Supervised, unsupervised, and hybrid learning models are used. It also discusses the challenges of large-scale AI system deployment, including the need for high-quality labelled datasets for training and computational resource constraints. The results suggest that AI-enabled anomaly detection could become a crucial part of IoT security, adapting to the growing number of connected devices.