| Title | Explainable Artificial Intelligence for Intrusion Detection in Internet of Things Networks: A Lightweight and Adaptive Security Framework |
| Research Area | Internet of Things |
| Abstract | The Internet of Things (IoT) has become an important component of modern digital infrastructure,
connecting sensors, industrial equipment, smart appliances, vehicles, healthcare devices, and urban
infrastructure. Although IoT provides substantial operational benefits, its large-scale deployment also
increases the potential attack surface of interconnected systems. Conventional security mechanisms
often struggle with the heterogeneous architecture, resource limitations, dynamic behavior, and
continuously changing traffic characteristics of IoT networks. Machine learning and deep learning
have consequently attracted significant attention for developing intelligent intrusion detection systems
capable of identifying anomalous and malicious activities. However, highly complex artificial
intelligence models can be difficult for security analysts to interpret, while computational requirements
may be unsuitable for resource-constrained IoT environments |
| Keywords | Internet of Things, Intrusion Detection System, Explainable Artificial Intelligence, Machine Learning, Deep Learning, Cybersecurity, Anomaly Detection, Edge Computing, TinyML, IoT Security |
| Paper Status | Published |
| Volume | 2 |
| Issue | 5 |
| Published On | 12/09/2026 |
| Published File |
IJSRTD_4893.pdf
|