Deep Neural Networks (DNNs) inherently exhibit a degree of robustness to bit-level faults due to their distributed representation of information. As a model increases in width, this information becomes more dispersed, theoretically reducing the impact of any single bit fault. In this paper, we empirically investigate the relationship between model width and robustness to Single Event Upsets (SEUs). We conduct a comprehensive experiment in which baseline models undergo iterative structured pruning to reduce their width while preserving task performance as much as possible. At each pruning stage, we run a targeted fault-injection campaign to evaluate the model's performance under simulated bit-flip scenarios. Our results show that, although structured pruning increases per-inference sensitivity to faults by reducing redundancy, this effect is effectively counterbalanced by shorter execution time, which lowers the probability of encountering an SEU. These findings suggest that structured pruning can yield significant energy and latency savings without compromising overall reliability, providing useful guidance for designing robust AI systems for space applications.
Figures & tables
Figure 1: Abstract representation of a simple Processing Element.
Figure 2: Flowchart of the iterative pruning and quantization methodology.
Parameter
ResNet-18
MobileNetV2
Dataset
EuroSAT [ 7 ]
Optimizer
SGD
Batch Size
128
Momentum
0.9
Weight Decay
1×10−4
LR Schedule γ
0.1
Table 1: Hyperparameters for Training, Pruning, and Quantization.
Neural network robustness studies how models withstand adversarial inputs, data shifts, noise, and hardware faults while maintaining reliable predictions.
Brandenburgische Technische Universität Cottbus-Senftenberg, Germany · Humboldt University of Berlin, Germany · Tallinn University of Technology, Tallinn, Estonia
Department of Mathematics Pennsylvania State University University Park, PA 16802, USA · Department of Computing and Mathematical Sciences California Institute of Technology Pasadena, CA 91125, USA