TensorFI: A Flexible Fault Injection Framework for TensorFlow Applications

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 (e.g., selective instruction duplication), a fun...

Full description

Saved in:
Bibliographic Details
Main Authors: Chen, Zitao, Narayanan, Niranjhana, Fang, Bo, Li, Guanpeng, Pattabiraman, Karthik, DeBardeleben, Nathan
Format: Conference Proceeding
Language:English
Subjects:
Fault Injection
Machine Learning
Resilience
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 (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. The results give us insights into why some of the models are more resilient. We also present two case studies to demonstrate the usefulness of the tool. TensorFI is publicly available at https://github.com/DependableSystemsLab/TensorFI.
ISSN:2332-6549
DOI:10.1109/ISSRE5003.2020.00047