As machine learning (ML) has seen increasing adoption in safety-critical domains (e.g., autonomous vehicles), the reliability of ML systems has also grown in importance. While prior studies have proposed techniques to enable efficient error-resilience techniques (e.g., selective instruction duplication), a fundamental requirement for realizing these techniques is a detailed understanding of the application's resilience. In this work, we present TensorFI, a high-level fault injection (FI) framework for TensorFlow-based applications. TensorFI is able to inject both hardware and software faults in general TensorFlow programs. TensorFI is a configurable FI tool that is flexible, easy to use, and portable. It can be integrated into existing TensorFlow programs to assess their resilience for different fault types (e.g., faults in particular operators). We use TensorFI to evaluate the resilience of 12 ML programs, including DNNs used in the autonomous vehicle domain. Our tool is publicly available at https://github.com/DependableSystemsLab/TensorFI.
@article{arxiv.2004.01743,
title = {TensorFI: A Flexible Fault Injection Framework for TensorFlow Applications},
author = {Zitao Chen and Niranjhana Narayanan and Bo Fang and Guanpeng Li and Karthik Pattabiraman and Nathan DeBardeleben},
journal= {arXiv preprint arXiv:2004.01743},
year = {2020}
}
Comments
A preliminary version of this work was published in a workshop