Unsupervised Contextual Anomaly Detection using Joint Deep Variational Generative Models
This addresses anomaly detection in data with contextual attributes, potentially useful for domains like cybersecurity or industrial monitoring, but appears incremental as it builds on existing VAE frameworks.
The paper tackles unsupervised contextual anomaly detection by proposing a method using a cross-linked pair of Variational Auto-Encoders to assign normality scores, enabling distinct separation of contextual and behavioral attributes and robustness to anomalous contexts without special pre-processing.
A method for unsupervised contextual anomaly detection is proposed using a cross-linked pair of Variational Auto-Encoders for assigning a normality score to an observation. The method enables a distinct separation of contextual from behavioral attributes and is robust to the presence of anomalous or novel contextual attributes. The method can be trained with data sets that contain anomalies without any special pre-processing.