Abstract

In the rapidly expanding Internet of Things (IoT) landscape, the security of IoT devices is a major concern. The challenge lies in the lack of intrusion detection systems (IDS) models for these devices. This is due to resource limitations, resulting in, single point of failure, delayed threat detection and privacy issues when centralizing IDS processing. To address this, a LiteDLVC model is proposed in this paper, employing a multi-layer perceptron (MLP) in a federated learning (FL) approach to minimize the vulnerabilities in IoT system. This model manages smaller datasets from individual devices, reducing processing time and optimizing computing resources. Importantly, in the event of an attack, the LiteDLVC model targets only the compromised device, protecting the FL aggregator and other IoT devices. The model's evaluation using the BoT-IoT dataset on TensorFlow Federated (TFF) demonstrates higher accuracy and better performance with full features subset of 99.99% accuracy on test set and achieved average of 1.11sec in detecting bot attacks through federated detection. While on 10-best subset achieved 99.99 on test with 1.14sec as average detection time. Notably, this highlights that LiteDLVC model can potential secure IoT device from device level very efficiently. To improve the global model convergence, we are currently exploring the use genetic algorithm.  This could lead to better performance on diverse IoT data distributions, and increased overall efficiency in FL scenes with non-IID data.