Guarded Deep Learning using Scenario-Based Modeling

TL;DR

This paper introduces a method to enhance the safety of deep neural networks by integrating scenario-based modeling to create human-understandable override rules that can be applied to DNN decisions.

Contribution

It presents a novel approach combining scenario-based modeling with DNNs to generate interpretable override rules for safer model deployment.

Findings

Override rules improve model safety and interpretability.

The approach is demonstrated on multiple DNN models.

Rules are comprehensible and expressive enough for practical use.

Abstract

Deep neural networks (DNNs) are becoming prevalent, often outperforming manually-created systems. Unfortunately, DNN models are opaque to humans, and may behave in unexpected ways when deployed. One approach for allowing safer deployment of DNN models calls for augmenting them with hand-crafted override rules, which serve to override decisions made by the DNN model when certain criteria are met. Here, we propose to bring together DNNs and the well-studied scenario-based modeling paradigm, by expressing these override rules as simple and intuitive scenarios. This approach can lead to override rules that are comprehensible to humans, but are also sufficiently expressive and powerful to increase the overall safety of the model. We describe how to extend and apply scenario-based modeling to this new setting, and demonstrate our proposed technique on multiple DNN models.