# Harden Deep Neural Networks Against Fault Injections Through Weight Scaling

arXiv: https://arxiv.org/abs/2411.18993 · HTML: https://mlsanity.com/paper/2411.18993/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 19 references that are in the map.
- First posted on arXiv 28 Nov 2024.

## Builds on (most cited first, 10 of 10)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [YOLOv10: Real-Time End-to-End Object Detection](https://mlsanity.com/paper/2405.14458/) (2024)
- [A Survey of Deep Learning Techniques for Autonomous Driving](https://mlsanity.com/paper/1910.07738/) (2019)
- [Terminal Brain Damage: Exposing the Graceless Degradation in Deep Neural Networks Under Hardware Fault Attacks](https://mlsanity.com/paper/1906.01017/) (2019)
- [Large Language Models for Medicine: A Survey](https://mlsanity.com/paper/2405.13055/) (2024)
- [Silent Data Corruptions at Scale](https://mlsanity.com/paper/2102.11245/) (2021)
- [In-Place Zero-Space Memory Protection for CNN](https://mlsanity.com/paper/1910.14479/) (2019)

## Built on by (most cited first, 2 of 2)

- [Maximal Brain Damage Without Data or Optimization: Disrupting Neural Networks via Sign-Bit Flips](https://mlsanity.com/paper/2502.07408/) (2025)
- [Quantum Tunneling-Aware Machine Learning: Physics-Derived Noise Models for Robust Deployment](https://mlsanity.com/paper/2606.00741/) (2026)

## Abstract (arXiv)

Deep neural networks (DNNs) have enabled smart applications on hardware devices. However, these hardware devices are vulnerable to unintended faults caused by aging, temperature variance, and write errors. These faults can cause bit-flips in DNN weights and significantly degrade the performance of DNNs. Thus, protection against these faults is crucial for the deployment of DNNs in critical applications. Previous works have proposed error correction codes based methods, however these methods often require high overheads in both memory and computation. In this paper, we propose a simple yet effective method to harden DNN weights by multiplying weights by constants before storing them to fault-prone medium. When used, these weights are divided back by the same constants to restore the original scale. Our method is based on the observation that errors from bit-flips have properties similar to additive noise, therefore by dividing by constants can reduce the absolute error from bit-flips. To demonstrate our method, we conduct experiments across four ImageNet 2012 pre-trained models along with three different data types: 32-bit floating point, 16-bit floating point, and 8-bit fixed point. This method demonstrates that by only multiplying weights with constants, Top-1 Accuracy of 8-bit fixed point ResNet50 is improved by 54.418 at bit-error rate of 0.0001.