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

2026-02-18

AI Summary

This study addresses the lack of systematic evaluation on the sensitivity of different numerical representations in embedded deep learning models under electromagnetic fault injection (EMFI) attacks. For the first time, it systematically compares the fault tolerance of 32/16-bit floating-point and 8/4-bit integer quantized parameters across ResNet-18/34/50 and VGG-11 models, using a low-cost EMFI platform to inject faults into low-power embedded chips. The results demonstrate that integer quantization significantly enhances model robustness: while floating-point models suffer near-complete accuracy collapse after a single fault injection, the 8-bit integer VGG-11 maintains approximately 70% Top-1 and 90% Top-5 accuracy, with this advantage becoming especially pronounced in larger networks.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Adversarial Learning & Robustness
• Natural Language Processing: Safety and Robustness

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Security and Privacy: Large-scale security measurements

Abstract

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. 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. Especially, when considering the the 8-bit representation on a relatively large network (VGG-11), the Top-1 accuracies stay at around 70% and the Top-5 at around 90%.

Problem

• EMFI
• number representation
• fault injection
• embedded deep learning
• model robustness

Innovation

• EMFI
• number representation
• fault injection
• embedded deep learning
• model robustness