Mitigating multiple single-event upsets during deep neural network inference using fault-aware training

Toon Vinck, Naïn Jonckers, Gert Dekkers, Jeffrey Prinzie, Peter Karsmakers
2/13/2025
cs.LG

No confident code implementation found for this paper.

Abstract

Deep neural networks (DNNs) are increasingly used in safety-critical applications. Reliable fault analysis and mitigation are essential to ensure their functionality in harsh environments that contain high radiation levels. This study analyses the impact of multiple single-bit single-event upsets in DNNs by performing fault injection at the level of a DNN model. Additionally, a fault aware training (FAT) methodology is proposed that improves the DNNs' robustness to faults without any modification to the hardware. Experimental results show that the FAT methodology improves the tolerance to faults up to a factor 3.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Enhancing Neural Network Robustness Against Fault Injection Through Non-linear Weight Transformations

87% match2024

Special Session: Approximation and Fault Resiliency of DNN Accelerators

85% match2023

eFAT: Improving the Effectiveness of Fault-Aware Training for Mitigating Permanent Faults in DNN Hardware Accelerators

85% match2023

Harden Deep Neural Networks Against Fault Injections Through Weight Scaling

84% match2024

FAQ: Mitigating the Impact of Faults in the Weight Memory of DNN Accelerators through Fault-Aware Quantization

84% match2023

ISimDL: Importance Sampling-Driven Acceleration of Fault Injection Simulations for Evaluating the Robustness of Deep Learning

84% match2023

Cite this paper

@article{vinck2025mitigating,
  title  = {Mitigating multiple single-event upsets during deep neural network inference using fault-aware training},
  author = {Toon Vinck and Naïn Jonckers and Gert Dekkers and Jeffrey Prinzie and Peter Karsmakers},
  year   = {2025},
  eprint = {2502.09374},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2502.09374v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2502.09374.svg)](https://codeofpaper.com/paper/2502.09374)

Discussion