# The Weight of a Bit: EMFI Sensitivity Analysis of Embedded Deep Learning Models

arXiv: https://arxiv.org/abs/2602.16309 · HTML: https://mlsanity.com/paper/2602.16309/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 40 references that are in the map.
- First posted on arXiv 18 Feb 2026.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A White Paper on Neural Network Quantization](https://mlsanity.com/paper/2106.08295/) (2021)
- [Pruning and Quantization for Deep Neural Network Acceleration: A Survey](https://mlsanity.com/paper/2101.09671/) (2021)
- [TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systems](https://mlsanity.com/paper/2010.08678/) (2020)
- [TBT: Targeted Neural Network Attack with Bit Trojan](https://mlsanity.com/paper/1909.05193/) (2019)
- [Bit-Flip Attack: Crushing Neural Network with Progressive Bit Search](https://mlsanity.com/paper/1903.12269/) (2019)
- [Terminal Brain Damage: Exposing the Graceless Degradation in Deep Neural Networks Under Hardware Fault Attacks](https://mlsanity.com/paper/1906.01017/) (2019)
- [Tiny Machine Learning: Progress and Futures](https://mlsanity.com/paper/2403.19076/) (2024)
- [SNIFF: Reverse Engineering of Neural Networks with Fault Attacks](https://mlsanity.com/paper/2002.11021/) (2020)
- [Understanding the Impact of Precision Quantization on the Accuracy and Energy of Neural Networks](https://mlsanity.com/paper/1612.03940/) (2016)
- [RADAR: Run-time Adversarial Weight Attack Detection and Accuracy Recovery](https://mlsanity.com/paper/2101.08254/) (2021)
- [DeepDyve: Dynamic Verification for Deep Neural Networks](https://mlsanity.com/paper/2009.09663/) (2020)
- [HASHTAG: Hash Signatures for Online Detection of Fault-Injection Attacks on Deep Neural Networks](https://mlsanity.com/paper/2111.01932/) (2021)
- [FooBaR: Fault Fooling Backdoor Attack on Neural Network Training](https://mlsanity.com/paper/2109.11249/) (2021)
- [Fault Injection on Embedded Neural Networks: Impact of a Single Instruction Skip](https://mlsanity.com/paper/2308.16665/) (2023)
- [DeepBaR: Fault Backdoor Attack on Deep Neural Network Layers](https://mlsanity.com/paper/2407.21220/) (2024)

## Built on by (most cited first, 1 of 1)

- [Characterizing the Fault Response of the Intel Neural Compute Stick 2 Under Single-Pulse Electromagnetic Fault Injection](https://mlsanity.com/paper/2605.22437/) (2026)

## Abstract (arXiv)

Fault injection attacks on embedded neural network models have been shown as a potent threat. Numerous works studied resilience of models from various points of view. As of now, there is no comprehensive study that would evaluate the influence of number representations used for model parameters against electromagnetic fault injection (EMFI) attacks. In this paper, we investigate how four different number representations influence the success of an EMFI attack on embedded neural network models. We chose two common floating-point representations (32-bit, and 16-bit), and two integer representations (8-bit, and 4-bit). We deployed four common image classifiers, ResNet-18, ResNet-34, ResNet-50, and VGG-11, on an embedded memory chip, and utilized a low-cost EMFI platform to trigger faults. Beyond accuracy evaluation, we characterize the injected fault pattern by analyzing the bit error rate, the spatial distribution of corrupted bytes, and the prevalence of 0xFE/0xFF byte values across formats, identifying the mechanisms responsible for the observed differences in resilience. Our results show that while floating-point representations exhibit almost a complete degradation in accuracy (Top-1 and Top-5) after a single fault injection, integer representations offer better resistance overall. In particular, the 8-bit representation on a relatively large network (VGG-11) retains Top-1 accuracy of around 70% and Top-5 at around 90%.