AIREPAIR: A Repair Platform for Neural Networks

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

79 Downloads (Pure)

Abstract

We present AIREPAIR, a platform for repairing neural networks. It features the integration of existing network repair tools. Based on AIREPAIR, one can run different repair methods on the same model, thus enabling the fair comparison of different repair techniques. In this paper, we evaluate AIREPAIR with five recent repair methods on popular deeplearning datasets and models. Our evaluation confirms the utility of AIREPAIR, by comparing and analyzing the results from
different repair techniques. A demonstration is available at https://youtu.be/UkKw5neeWhw.
Original languageEnglish
Title of host publication45th IEEE/ACM International Conference on Software Engineering
Publication statusAccepted/In press - 20 Jan 2023

Fingerprint

Dive into the research topics of 'AIREPAIR: A Repair Platform for Neural Networks'. Together they form a unique fingerprint.

Cite this