# Machine Learning in Space: Surveying the Robustness of on-board ML models to Radiation

arXiv: https://arxiv.org/abs/2405.02642 · HTML: https://mlsanity.com/paper/2405.02642/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 160 references that are in the map.
- First posted on arXiv 4 May 2024.

## Builds on (most cited first, 23 of 23)

- [One pixel attack for fooling deep neural networks](https://mlsanity.com/paper/1710.08864/) (2017)
- [Kornia: an Open Source Differentiable Computer Vision Library for PyTorch](https://mlsanity.com/paper/1910.02190/) (2019)
- [Bit-Flip Attack: Crushing Neural Network with Progressive Bit Search](https://mlsanity.com/paper/1903.12269/) (2019)
- ["Real Attackers Don't Compute Gradients": Bridging the Gap Between Adversarial ML Research and Practice](https://mlsanity.com/paper/2212.14315/) (2022)
- [A Survey on Deep Learning-Based Monocular Spacecraft Pose Estimation: Current State, Limitations and Prospects](https://mlsanity.com/paper/2305.07348/) (2023)
- [Cloud-Net: An end-to-end Cloud Detection Algorithm for Landsat 8 Imagery](https://mlsanity.com/paper/1901.10077/) (2019)
- [TensorFI: A Flexible Fault Injection Framework for TensorFlow Applications](https://mlsanity.com/paper/2004.01743/) (2020)
- [On-Board Federated Learning for Dense LEO Constellations](https://mlsanity.com/paper/2111.12769/) (2021)
- [The Final Frontier: Deep Learning in Space](https://mlsanity.com/paper/2001.10362/) (2020)
- [One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training](https://mlsanity.com/paper/2308.07934/) (2023)
- [Adversarial Attacks against a Satellite-borne Multispectral Cloud Detector](https://mlsanity.com/paper/2112.01723/) (2021)
- [On Board Volcanic Eruption Detection through CNNs and Satellite Multispectral Imagery](https://mlsanity.com/paper/2106.15281/) (2021)
- [Accelerating Deep Learning Applications in Space](https://mlsanity.com/paper/2007.11089/) (2020)
- [Cloud and Cloud Shadow Segmentation for Remote Sensing Imagery via Filtered Jaccard Loss Function and Parametric Augmentation](https://mlsanity.com/paper/2001.08768/) (2020)
- [Selected Trends in Artificial Intelligence for Space Applications](https://mlsanity.com/paper/2212.06662/) (2022)
- [Spacecraft Autonomous Decision-Planning for Collision Avoidance: a Reinforcement Learning Approach](https://mlsanity.com/paper/2310.18966/) (2023)
- [Characterizing a Neutron-Induced Fault Model for Deep Neural Networks](https://mlsanity.com/paper/2211.13094/) (2022)
- [Reconfigurable Intelligent Surfaces in Action for Non-Terrestrial Networks](https://mlsanity.com/paper/2012.00968/) (2020)
- [Autonomous crater detection on asteroids using a fully-convolutional neural network](https://mlsanity.com/paper/2204.00477/) (2022)
- [Death By A Thousand COTS: Disrupting Satellite Communications using Low Earth Orbit Constellations](https://mlsanity.com/paper/2204.13514/) (2022)
- [Towards a Unified Cybersecurity Testing Lab for Satellite, Aerospace, Avionics, Maritime, Drone (SAAMD) technologies and communications](https://mlsanity.com/paper/2302.08359/) (2023)
- [Watch This Space: Securing Satellite Communication through Resilient Transmitter Fingerprinting](https://mlsanity.com/paper/2305.06947/) (2023)
- [CLExtract: Recovering Highly Corrupted DVB/GSE Satellite Stream with Contrastive Learning](https://mlsanity.com/paper/2310.08210/) (2023)

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

- [Advancing Earth Observation: A Survey on AI-Powered Image Processing in Satellites](https://mlsanity.com/paper/2501.12030/) (2025)
- [FPGA-Enabled Machine Learning Applications in Earth Observation: A Systematic Review](https://mlsanity.com/paper/2506.03938/) (2025)
- [Hardware-Aware Deployment of Joint SAR Compression and Despeckling on FPGA](https://mlsanity.com/paper/2608.11271/) (2026)

## Abstract (arXiv)

Modern spacecraft are increasingly relying on machine learning (ML). However, physical equipment in space is subject to various natural hazards, such as radiation, which may inhibit the correct operation of computing devices. Despite plenty of evidence showing the damage that naturally-induced faults can cause to ML-related hardware, we observe that the effects of radiation on ML models for space applications are not well-studied. This is a problem: without understanding how ML models are affected by these natural phenomena, it is uncertain "where to start from" to develop radiation-tolerant ML software. As ML researchers, we attempt to tackle this dilemma. By partnering up with space-industry practitioners specialized in ML, we perform a reflective analysis of the state of the art. We provide factual evidence that prior work did not thoroughly examine the impact of natural hazards on ML models meant for spacecraft. Then, through a "negative result", we show that some existing open-source technologies can hardly be used by researchers to study the effects of radiation for some applications of ML in satellites. As a constructive step forward, we perform simple experiments showcasing how to leverage current frameworks to assess the robustness of practical ML models for cloud detection against radiation-induced faults. Our evaluation reveals that not all faults are as devastating as claimed by some prior work. By publicly releasing our resources, we provide a foothold -- usable by researchers without access to spacecraft -- for spearheading development of space-tolerant ML models.