# SPINE: A Fault Injection Profiler for Quantized Neural Networks under Accumulated Faults

arXiv: https://arxiv.org/abs/2606.19526 · HTML: https://mlsanity.com/paper/2606.19526/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 24 references that are in the map.
- First posted on arXiv 17 Jun 2026.

## Builds on (most cited first, 4 of 4)

- [Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations](https://mlsanity.com/paper/1609.07061/) (2016)
- [DeepSat - A Learning framework for Satellite Imagery](https://mlsanity.com/paper/1509.03602/) (2015)
- [When Single Event Upset Meets Deep Neural Networks: Observations, Explorations, and Remedies](https://mlsanity.com/paper/1909.04697/) (2019)
- [NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes](https://mlsanity.com/paper/2306.16869/) (2023)

## Abstract (arXiv)

Deploying deep neural networks at the edge demands efficient inference under strict cost and power constraints. Quantized neural networks address these demands by replacing floating-point parameters with low-precision integers, yet their weights remain continuously exposed to radiation-induced bit-flips during inference. Fault Injection can be used to simulate those environments, but existing studies fail to characterize how accumulated upsets translate into mispredictions under realistic memory layouts. This paper presents a GDB-driven profiling framework that injects cumulative weight bit-flips directly onto the target binary of edge CPUs, generating per-layer fault profiles without requiring model retraining or code modification. Evaluated across multiple topologies, quantization efforts, and memory layouts, the results indicate how selective hardening strategies should be applied to effectively protect neural networks.