Fault Injection for TensorFlow Applications

doi:10.1109/TDSC.2022.3175930

Fault Injection for TensorFlow Applications

2023-07-01

8

OA

AI

N

Niranjhana Narayanan *

DOI：10.1109/TDSC.2022.3175930

Original

Original request for help

Save

Abstract

En 中文

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 1 and TensorFI 2, high-level fault injection (FI) frameworks for TensorFlow-based applications. TensorFI 1 and 2 are able to inject both hardware and software faults in any general TensorFlow 1 and 2 program respectively. Both are configurable FI tools that are flexible, easy to use, and portable. They can be integrated into existing TensorFlow programs to assess their resilience for different fault types (e.g., bit-flips in particular operations or layers). We use TensorFI 1 and TensorFI 2 to evaluate the resilience of 11 and 10 ML programs respectively, all written in TensorFlow, including DNNs used in the autonomous vehicle domain. The results give us insights into why some of the models are more resilient. We also measure the performance overheads of the two injectors, and present 4 case studies, two for each tool, to demonstrate their utility.

Keywords:

Deep neural networks

error resilience

fault injection

machine learning

TensorFlow

Fault Injection for TensorFlow Applications

Abstract

Journal

Organization