# Enhancing Deep Learning with Scenario-Based Override Rules: a Case Study

arXiv: https://arxiv.org/abs/2301.08114 · HTML: https://mlsanity.com/paper/2301.08114/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 64 references that are in the map.
- First posted on arXiv 19 Jan 2023.

## Builds on (most cited first, 12 of 12)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [Practical Black-Box Attacks against Machine Learning](https://mlsanity.com/paper/1602.02697/) (2016)
- [Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving](https://mlsanity.com/paper/1610.03295/) (2016)
- [Constrained Reinforcement Learning for Robotics via Scenario-Based Programming](https://mlsanity.com/paper/2206.09603/) (2022)
- [Autonomics: In Search of a Foundation for Next Generation Autonomous Systems](https://mlsanity.com/paper/1911.07133/) (2019)
- [Scenario-Assisted Deep Reinforcement Learning](https://mlsanity.com/paper/2202.04337/) (2022)
- [Guarded Deep Learning using Scenario-Based Modeling](https://mlsanity.com/paper/2006.03863/) (2020)
- [On-the-Fly Construction of Composite Events in Scenario-Based Modeling using Constraint Solvers](https://mlsanity.com/paper/1909.00408/) (2019)
- [Context-Oriented Behavioral Programming](https://mlsanity.com/paper/2005.02373/) (2020)
- [BPjs --- a framework for modeling reactive systems using a scripting language and BP](https://mlsanity.com/paper/1806.00842/) (2018)

## Built on by (most cited first, 2 of 2)

- [DEM: A Method for Certifying Deep Neural Network Classifier Outputs in Aerospace](https://mlsanity.com/paper/2401.02283/) (2024)
- [On Integrating Large Language Models and Scenario-Based Programming for Improving Software Reliability](https://mlsanity.com/paper/2509.09194/) (2025)

## Abstract (arXiv)

Deep neural networks (DNNs) have become a crucial instrument in the software development toolkit, due to their ability to efficiently solve complex problems. Nevertheless, DNNs are highly opaque, and can behave in an unexpected manner when they encounter unfamiliar input. One promising approach for addressing this challenge is by extending DNN-based systems with hand-crafted override rules, which override the DNN's output when certain conditions are met. Here, we advocate crafting such override rules using the well-studied scenario-based modeling paradigm, which produces rules that are simple, extensible, and powerful enough to ensure the safety of the DNN, while also rendering the system more translucent. We report on two extensive case studies, which demonstrate the feasibility of the approach; and through them, propose an extension to scenario-based modeling, which facilitates its integration with DNN components. We regard this work as a step towards creating safer and more reliable DNN-based systems and models.