Back to Search Start Over

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

Authors :
Zhang, Guanqin
Sun, Jiankun
Xu, Feng
Bandara, H. M. N. Dilum
Chen, Shiping
Sui, Yulei
Menzies, Tim
Publication Year :
2022

Abstract

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.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2211.10012
Document Type :
Working Paper
Full Text :
https://doi.org/10.1109/MC.2022.3223646