Fault Injectors for TensorFlow: Evaluation of the Impact of Random Hardware Faults on Deep CNNs

TL;DR

This paper introduces two fault injection frameworks for TensorFlow that evaluate the impact of random hardware faults on deep CNNs, aiding in understanding and improving fault tolerance in safety-critical AI applications.

Contribution

The paper presents novel fault injection tools for TensorFlow 1 and 2, enabling configurable fault testing on neural networks to assess their robustness against hardware faults.

Findings

Random bit flips significantly affect classification accuracy.

Certain layers and operations are more critical to network reliability.

Frameworks help identify critical components for fault tolerance.

Abstract

Today, Deep Learning (DL) enhances almost every industrial sector, including safety-critical areas. The next generation of safety standards will define appropriate verification techniques for DL-based applications and propose adequate fault tolerance mechanisms. DL-based applications, like any other software, are susceptible to common random hardware faults such as bit flips, which occur in RAM and CPU registers. Such faults can lead to silent data corruption. Therefore, it is crucial to develop methods and tools that help to evaluate how DL components operate under the presence of such faults. In this paper, we introduce two new Fault Injection (FI) frameworks InjectTF and InjectTF2 for TensorFlow 1 and TensorFlow 2, respectively. Both frameworks are available on GitHub and allow the configurable injection of random faults into Neural Networks (NN). In order to demonstrate the feasibility of the frameworks, we also present the results of FI experiments conducted on four VGG-based Convolutional NNs using two image sets. The results demonstrate how random bit flips in the output of particular mathematical operations and layers of NNs affect the classification accuracy. These results help to identify the most critical operations and layers, compare the reliability characteristics of functionally similar NNs, and introduce selective fault tolerance mechanisms.