Provable Guarantees for Deep Learning-Based Anomaly Detection through Logical Constraints

Abstract

Incorporating constraints expressed as logical formulas and based on foundational prior knowledge into deep learning models can provide formal guarantees for the fulfillment of critical model properties, improve model performance, and ensure that relevant structures can be inferred from less data. We propose to thoroughly explore such logical constraints over input-output relations in the context of deep learning-based anomaly detection, specifically by extending the capabilities of the MultiplexNet framework.