Artificial Neural Networks for Space and Safety-Critical Applications: Reliability Issues and Potential Solutions
Open accessThe DOI matches its Crossref record; 165 of the 165 references it cites were found in a registry or an index.
Abstract
Machine Learning is among the greatest advancements in computer science and engineering and is today used to classify or detect objects, a key feature in autonomous vehicles. Since neural networks are heavily used in safety-critical applications, such as automotive and aerospace, their reliability must be paramount. However, the reliability evaluation of neural network systems is extremely challenging due to the complexity of the software, which is composed of hundreds of layers, and of the underlying hardware, typically a parallel device or an embedded accelerator. This paper reviews fundamental concepts of Artificial Intelligence, Deep Neural Network, and parallel computing device reliability. Then, the reliability studies that consider the radiation effects in the hardware, their propagation through the computing architecture, and their final impact on the software output are summarized. A detailed survey of the available strategies to measure the sensitivity of neural network frameworks and to observe fault propagation is given, together with a summary of the data obtained so far. Finally, a discussion on how to use the experimental evaluation to design effective and efficient hardening solutions for Artificial Neural Networks is provided. The available hardening solutions are critically reviewed, highlighting their benefits and drawbacks.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures

![Fig. 2 Visualization of the structure of a Convolutional Neural Network. The Convolution layers extract features from the input, ReLU operations ensure nonlinear input-output correlation, Pooling layers reduce the amount of data propagated, the fully connected layers use the output of previous layers to detect and classify objects. Taken from [20].](https://figures.cochat.ai/paper-figures/388e069ff2494ad09ac19f612ef4cf71/artificial-neural-networks-for-space-and-safety-critical-applications-figure-2.png)
![Fig. 3 Example of the convolution operation. The convolution needs to be performed in every window of the input feature map and, thus, is highly computationally demanding. Adapted from [20].](https://figures.cochat.ai/paper-figures/fa68a0df203b4c1da85a2dcb67fb868b/artificial-neural-networks-for-space-and-safety-critical-applications-figure-3.png)
![Fig. 4 Example of features extracted by the convolution layers from the input image and of the effect of ReLu and Pooling. Taken from [24].](https://figures.cochat.ai/paper-figures/6f98d304f646437cb9752261054733ca/artificial-neural-networks-for-space-and-safety-critical-applications-figure-4.png)


![Fig. 7 Simplified view of the architecture of FPGAs, showing the programmable elements used to define a circuit to be executed [39].](https://figures.cochat.ai/paper-figures/132b1c97074f43a6b45e7a231244ba99/artificial-neural-networks-for-space-and-safety-critical-applications-figure-7.png)

![Fig. 9 High level schematic of the Coral Edge TPU architecture, which is basically composed of a hardwired systolic array. Adapted from [5].](https://figures.cochat.ai/paper-figures/3d3e9e8ae3454248be614c6a5ac1dba2/artificial-neural-networks-for-space-and-safety-critical-applications-figure-9.png)








![Fig. 14 Description of the basic concept of ABFT applied to matrix multiplication (top) and smart pooling (bottom). These hardening solutions are highly effective in reducing the impact of radiation in CNNs execution [11].](https://figures.cochat.ai/paper-figures/8ec597ef1be643e1bd599367ec22befb/artificial-neural-networks-for-space-and-safety-critical-applications-figure-14.png)

![Fig. 15 Structure of the error detection framework implemented comparing subsequent input images and the correspondent detection. Similar input frames should provide similar detection [168].](https://figures.cochat.ai/paper-figures/a96c2dc29d654076aecd4552e977dc76/artificial-neural-networks-for-space-and-safety-critical-applications-figure-15.png)

![Fig. 16 Redundant low-precision functional units can be used to implement efficient DWC strategies. On GPUs, when a code is executed in a given precision the functional units of different precision are idle and can be leveraged for duplication [176].](https://figures.cochat.ai/paper-figures/19eadf11215f4ef9b3ca7de6edbd748c/artificial-neural-networks-for-space-and-safety-critical-applications-figure-16.png)
![Fig. 17 Fault-aware training is a promising solution to make the DNN more reliable [179].](https://figures.cochat.ai/paper-figures/938aa1612db34527a56655d229656546/artificial-neural-networks-for-space-and-safety-critical-applications-figure-17.png)
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“For safety-critical systems, explainability is not enough for a system to be trustworthy.Various requirements such as robustness, reliability, traceability, data quality, and other factors must be demonstrated [25,43,62,63].”
From A requirements model for AI algorithms in functional safety-critical systems with an explainable self-enforcing network from a developer perspective (2024) · cites this paper as [62]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
MobileNetV2: Inverted Residuals and Linear Bottlenecks
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00474 · Cited by 28,755 · cited 1×
“Building upon this function, several other ReLU-like activations have been developed, e.g., the scaled exponential linear unit (SELU) [27], the Gaussian error linear unit (GELU) [28], and ReLU6 [29].”
BackgroundAn introduction to ROC analysis
Fawcett, T. (2006) · Pattern Recognition Letters · doi:10.1016/j.patrec.2005.10.010 · Cited by 21,879 · cited 2×
“To evaluate error criticality for detection, it is necessary to consider the BB’s area, adopting the methodology used in the image processing community [61].”
MethodLarge-Scale Machine Learning with Stochastic Gradient Descent
Bottou, L. (2010) · Proceedings of COMPSTAT'2010 · doi:10.1007/978-3-7908-2604-3_16 · Cited by 5,795 · cited 1×
“Given the gradients, an optimizer, e.g., stochastic gradient descent [23], updates the weights in order to minimize the loss function.”
MethodBasic concepts and taxonomy of dependable and secure computing
Avizienis, A., Laprie, J.-C., Randell, B., & Landwehr, C. (2004) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2004.2 · Cited by 5,223 · cited 1×
“In this work, we will use the taxonomy defined by Avizienis et al. [60].”
MethodBackpropagation through time: what it does and how to do it
Werbos, P. J. (1990) · Proceedings of the IEEE · doi:10.1109/5.58337 · Cited by 4,879 · cited 1×
“ANNs are universal function approximators that, thanks to Backpropagation (short for backward propagation of errors) training [20], [21], [22] and sufficient network complexity, enable the solution of a variety of tasks, e.g., classification, detection, and regression.”
BackgroundGaussian Error Linear Units (GELUs)
Hendrycks, D., & Gimpel, K. (2016) · arXiv · doi:10.48550/arxiv.1606.08415 · Cited by 3,537 · cited 1×
“Building upon this function, several other ReLU-like activations have been developed, e.g., the scaled exponential linear unit (SELU) [27], the Gaussian error linear unit (GELU) [28], and ReLU6 [29].”
BackgroundDeep Learning using Rectified Linear Units (ReLU)
Agarap, A. F. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.08375 · Cited by 2,399 · cited 1×
“…most computationally demanding and, thus, vulnerable to radiation), activation functions are used for ensuring a nonlinear input–output relationship in DNNs and are very often implemented through rectified linear units (ReLUs) [25] ReLU ( x ) = max ( 0 , x ), where x stands for the input tensor.”
MethodSelf-Normalizing Neural Networks
Klambauer, G., Unterthiner, T., Mayr, A., & Hochreiter, S. (2017) · arXiv · doi:10.48550/arxiv.1706.02515 · Cited by 2,267 · cited 1×
“Building upon this function, several other ReLU-like activations have been developed, e.g., the scaled exponential linear unit (SELU) [27], the Gaussian error linear unit (GELU) [28], and ReLU6 [29].”
BackgroundNVIDIA Tesla: A Unified Graphics and Computing Architecture
Lindholm, E., Nickolls, J., Oberman, S., & Montrym, J. (2008) · IEEE Micro · doi:10.1109/mm.2008.31 · Cited by 1,362 · cited 1×
“Each basic computing unit (named CUDA core in NVIDIA devices) in the SM executes one thread with dedicated registers, avoiding complex resource sharing or the need for long pipelines [37] [see Fig.”
BackgroundPattern Recognition and Machine Learning
Maindonald, J. (2007) · Journal of Statistical Software · doi:10.18637/jss.v017.b05 · Cited by 1,349
Research works printed but not linked: 16
- 2023, NVIDIA Ampere GPU Whitepaper
- 2023, Google Coral Edge TPU Explained in Depth
- 2018, NVIDIA Jetson AGX Xavier Developer Kit | NVIDIA Developer
- 2011, Preview Road Vehicles Functional Safety
- Sumit, 2018, A Comprehensive Guide to Convolutional Neural Networks
- University, 2023, CS231n Convolutional Neural Networks for Visual Recognition
- Bengio, 2017, Deep Learning, 1
- 2022, Zynq-7000 All Programmable SoC
- 2006, Measurement and Reporting of Alpha Particle and Terrestrial Cosmic Ray-Induced Soft Errors in Semiconductor Devices
- Ziegler, 2004, SER—History, Trends and Challenges: A Guide for Designing With Memory ICs
- 2020, NVBitFI: An Architecture-level Fault Injection Tool for GPU Application Resilience Evaluations
- 2016, ESCC Basic Specification No. 22900
- 2016, Carol Radiation Setup
- Wyrwas, 2022, Proton Testing of AMD v1202b System on Chip
- Wyrwas, 2022, Radiation Effects and Analysis Lessons: A Scientist’s Field Instruction to Explain Radiation Testing
- Navarro, 2021, High-Performance Compute Board—A Fault-Tolerant Module for On-Boards Vision Processing
Cited by
Friha, O., Amine Ferrag, M., Kantarci, B., Cakmak, B., Ozgun, A., & Ghoualmi-Zine, N. (2024) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2024.3456549 · Cited by 189
Diana, L., & Dini, P. (2024) · Remote Sensing · doi:10.3390/rs16213957 · Cited by 57
Key Considerations for Real-Time Object Recognition on Edge Computing Devices
Surantha, N., & Sutisna, N. (2025) · Applied Sciences · doi:10.3390/app15137533 · Cited by 56
AdAM: Adaptive Approximate Multiplier for Fault Tolerance in DNN Accelerators
Taheri, M., Cherezova, N., Nazari, S., Azarpeyvand, A., Ghasempouri, T., Daneshtalab, M., Raik, J., & Jenihhin, M. (2024) · IEEE Transactions on Device and Materials Reliability · doi:10.1109/tdmr.2024.3523386 · Cited by 25
Reliability of Vision Transformers and CNNs on Edge AI Systems Under Neutron Radiation
Badia, J. M., Martin-Salinas, I., Leon, G., Amor-Martin, A., Frias-Dominguez, L., Belloch, J. A., Garcia-Valderas, M., Lindoso, A., Cazzaniga, C., & Entrena, L. (2025) · IEEE Transactions on Nuclear Science · doi:10.1109/tns.2025.3536519 · Cited by 11
“Several surveys summarize, analyze, and categorize many of these works [8], [11], [23], [24], [25], [26].”
Influential
Metadata
- Authors
- Rech, P.
- Affiliations
- University of Trento (IT)
- Corresponding author
- Rech, Paolo
- ORCID
- Rech, Paolo
- Venue
- IEEE Transactions on Nuclear Science
- Published
- 2024-04
- Volume
- 71
- Issue
- 4
- Pages
- 377-404
- ISSN
- 0018-9499 (ISSN-L)
- 1558-1578
- OpenAlex
- W4390576801
- Cited by
- 75
- References
- 165
- Citations by year
- 2026: 33 · 2025: 29 · 2024: 12
- FWCI
- 7.65
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- IEEE Transactions on Nuclear Science (publishedVersion, cc-by-nc-nd)
- Institutional Research Information System (Università degli Studi di Trento) (submittedVersion)
- ePubs (Science and Technology Facilities Council, Research Councils UK) (submittedVersion, cc-by-nc-nd)
- Funders
- U.S. Department of Energy
- Università degli Studi di Trento
- Universidade Federal do Rio Grande do Sul
- Los Alamos National Laboratory
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Radiation Effects in Electronics
- Physical Sciences › Computer Science › Software › Software Reliability and Analysis Research
- Physical Sciences › Computer Science › Hardware and Architecture › VLSI and Analog Circuit Testing
- Keywords
- artificial neural networks, deep neural network, reliability, safety-critical systems, space applications, radiation effects, fault propagation, fault tolerance, hardware reliability, fault sensitivity analysis, autonomous vehicles, aerospace
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Artificial Neural Networks for Space and Safety-Critical Applications: Reliability Issues and Potential Solutions. https://app.cochat.ai/papers/10.1109/tns.2024.3349956
- The paper
- Rech, P. (2024). Artificial Neural Networks for Space and Safety-Critical Applications: Reliability Issues and Potential Solutions. IEEE Transactions on Nuclear Science. https://doi.org/10.1109/tns.2024.3349956
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.