# Designing DNNs for a trade-off between robustness and processing performance in embedded devices

arXiv: https://arxiv.org/abs/2412.03682 · HTML: https://mlsanity.com/paper/2412.03682/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 13 references that are in the map.
- First posted on arXiv 4 Dec 2024.

## Builds on (most cited first, 7 of 7)

- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [A survey on modern trainable activation functions](https://mlsanity.com/paper/2005.00817/) (2020)
- [Terminal Brain Damage: Exposing the Graceless Degradation in Deep Neural Networks Under Hardware Fault Attacks](https://mlsanity.com/paper/1906.01017/) (2019)
- [A Systematic Literature Review on Hardware Reliability Assessment Methods for Deep Neural Networks](https://mlsanity.com/paper/2305.05750/) (2023)
- [HSI-Drive v2.0: More Data for New Challenges in Scene Understanding for Autonomous Driving](https://mlsanity.com/paper/2411.17530/) (2024)
- [Exploration of Activation Fault Reliability in Quantized Systolic Array-Based DNN Accelerators](https://mlsanity.com/paper/2401.09509/) (2024)
- [Rapid Deployment of Domain-specific Hyperspectral Image Processors with Application to Autonomous Driving](https://mlsanity.com/paper/2411.17543/) (2024)

## Built on by (most cited first, 3 of 3)

- [Hyperspectral Sensors and Autonomous Driving: Technologies, Limitations, and Opportunities](https://mlsanity.com/paper/2508.19905/) (2025)
- [Multi-Scale Spectral Attention Module-based Hyperspectral Segmentation in Autonomous Driving Scenarios](https://mlsanity.com/paper/2506.18682/) (2025)
- [DoCIA: An Online Document-Level Context Incorporation Agent for Speech Translation](https://mlsanity.com/paper/2504.05122/) (2025)

## Abstract (arXiv)

Machine learning-based embedded systems employed in safety-critical applications such as aerospace and autonomous driving need to be robust against perturbations produced by soft errors. Soft errors are an increasing concern in modern digital processors since smaller transistor geometries and lower voltages give electronic devices a higher sensitivity to background radiation. The resilience of deep neural network (DNN) models to perturbations in their parameters is determined, to a large extent, by the structure of the model itself, and also by the selected numerical representation and used arithmetic precision. When compression techniques such as model pruning and model quantization are applied to reduce memory footprint and computational complexity for deployment, both model structure and numerical representation are modified and thus, soft error robustness also changes. In this sense, although the choice of activation functions (AFs) in DNN models is frequently ignored, it conditions not only their accuracy and trainability, but also compressibility rates and numerical robustness. This paper investigates the suitability of using bounded AFs to improve model robustness against DNN parameter perturbations, assessing at the same time the impact of this choice on deployment in terms of model accuracy, compressibility, and computational burden. In particular, we analyze encoder-decoder fully convolutional models aimed at performing semantic segmentation tasks on hyperspectral images for scene understanding in autonomous driving. Deployment characterization is performed experimentally on an AMD-Xilinx's KV260 SoM.