AIREPAIR: A Repair Platform for Neural Networks
This work provides a tool for researchers and practitioners to systematically compare neural network repair methods, but it is incremental as it builds on existing techniques without introducing new repair methods.
The authors introduced AIREPAIR, a platform that integrates existing neural network repair tools to enable fair comparison of different repair techniques on the same models and datasets, confirming its utility through evaluation with three state-of-the-art tools.
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. We evaluate AIREPAIR with three state-of-the-art repair tools on popular deep-learning 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.