# A Tale of Two Cities: Data and Configuration Variances in Robust Deep Learning

arXiv: https://arxiv.org/abs/2211.10012 · HTML: https://mlsanity.com/paper/2211.10012/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 40 references that are in the map.
- First posted on arXiv 18 Nov 2022.

## Builds on (most cited first, 8 of 8)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [Reinforcement Learning for Combinatorial Optimization: A Survey](https://mlsanity.com/paper/2003.03600/) (2020)
- [Deep Forecast: Deep Learning-based Spatio-Temporal Forecasting](https://mlsanity.com/paper/1707.08110/) (2017)
- [Better Data Labelling with EMBLEM (and how that Impacts Defect Prediction)](https://mlsanity.com/paper/1905.01719/) (2019)
- ["Sampling"' as a Baseline Optimizer for Search-based Software Engineering](https://mlsanity.com/paper/1608.07617/) (2016)
- [Omni: Automated Ensemble with Unexpected Models against Adversarial Evasion Attack](https://mlsanity.com/paper/2011.12720/) (2020)

## Abstract (arXiv)

Deep neural networks (DNNs), are widely used in many industries such as image recognition, supply chain, medical diagnosis, and autonomous driving. However, prior work has shown the high accuracy of a DNN model does not imply high robustness (i.e., consistent performances on new and future datasets) because the input data and external environment (e.g., software and model configurations) for a deployed model are constantly changing. Hence, ensuring the robustness of deep learning is not an option but a priority to enhance business and consumer confidence. Previous studies mostly focus on the data aspect of model variance. In this article, we systematically summarize DNN robustness issues and formulate them in a holistic view through two important aspects, i.e., data and software configuration variances in DNNs. We also provide a predictive framework to generate representative variances (counterexamples) by considering both data and configurations for robust learning through the lens of search-based optimization.