Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

7-2023

Abstract

Recently, neural networks have spread into numerous fields including many safety-critical systems. Neural networks are built (and trained) by programming in frameworks such as TensorFlow and PyTorch. Developers apply a rich set of pre-defined layers to manually program neural networks or to automatically generate them (e.g., through AutoML). Composing neural networks with different layers is error-prone due to the non-trivial constraints that must be satisfied in order to use those layers. In this work, we propose an approach to automatically repair erroneous neural networks. The challenge is in identifying a minimal modification to the network so that it becomes valid. Modifying a layer might have cascading effects on subsequent layers and thus our approach must search recursively to identify a ”globally” minimal modification. Our approach is based on an executable semantics of deep learning layers and focuses on four kinds of errors which are common in practice. We evaluate our approach for two usage scenarios, i.e., repairing automatically generated neural networks and manually written ones suffering from common model bugs. The results show that we are able to repair 100% of a set of randomly generated neural networks (which are produced with an existing AI framework testing approach) effectively and efficiently (with an average repair time of 21.08s) and 93.75% of a collection of real neural network bugs (with an average time of 3min 40s).

Keywords

automatic AI model repair, deep learning models, semantics, specification, AI model generation, neural network generation, TensorFlow, Prolog

Discipline

Artificial Intelligence and Robotics | Software Engineering

Research Areas

Software and Cyber-Physical Systems

Publication

ISSTA 2023: Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis, Seattle, WA, July 17-21

First Page

150

Last Page

162

ISBN

9798400702211

Identifier

10.1145/3597926.3598045

Publisher

ACM

City or Country

New York

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1145/3597926.3598045

Download

Share

COinS