One-class IoT anomaly detection system using an improved interpolated deep SVDD autoencoder with adversarial regularizer

Abstract

The rapid proliferation of Internet of Things (IoT) devices and their integration into various sectors have significantly increased their exposure to security threats. Traditional Machine Learning (ML) methods, as well as some Deep Learning (DL) approaches, often fall short in addressing the unique challenges posed by contemporary IoT datasets, such as non-homogeneity, disparity, and high dimensionality. To tackle these challenges, this paper introduces a novel anomaly detection system specifically designed for IoT environments. The proposed model focused on optimizing the projected latent space to produce more effective separating hyperspheres, which will significantly improve the precision and robustness of anomaly detection. Experimental evaluation of multiple IoT datasets demonstrates that the system is capable of achieving state-of-the-art results compared to other shallow and deep learning approaches.