Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

5-2022

Abstract

Neural networks have had discernible achievements in a wide range of applications. The wide-spread adoption also raises the concern of their dependability and reliability. Similar to traditional decision-making programs, neural networks can have defects that need to be repaired. The defects may cause unsafe behaviors, raise security concerns or unjust societal impacts. In this work, we address the problem of repairing a neural network for desirable properties such as fairness and the absence of backdoor. The goal is to construct a neural network that satisfies the property by (minimally) adjusting the given neural network's parameters (i.e., weights). Specifically, we propose CARE (CAusality-based REpair), a causality-based neural network repair technique that 1) performs causality-based fault localization to identify the 'guilty' neurons and 2) optimizes the parameters of the identified neurons to reduce the misbehavior. We have empirically evaluated CARE on various tasks such as backdoor removal, neural network repair for fairness and safety properties. Our experiment results show that CARE is able to repair all neural networks efficiently and effectively. For fairness repair tasks, CARE successfully improves fairness by 61.91 % on average. For backdoor removal tasks, CARE reduces the attack success rate from over 98% to less than 1 %. For safety property repair tasks, CARE reduces the property violation rate to less than 1 %. Results also show that thanks to the causality-based fault localization, CARE's repair focuses on the misbehavior and preserves the accuracy of the neural networks.

Keywords

Fault Localization, Machine Learning with and for SE, Program Repair

Discipline

Databases and Information Systems | Software Engineering

Research Areas

Software and Cyber-Physical Systems

Publication

ASCE '22: Proceedings of the 44th International Conference on Software Engineering, Pittsburgh, May 8-20

First Page

338

Last Page

349

ISBN

9781450392211

Identifier

10.1145/3510003.3510080

Publisher

ACM

City or Country

New York

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1145/3510003.3510080

Share

COinS