mlsanityData to 7 Oct 2026

Adversarial Attacks against a Satellite-borne Multispectral Cloud Detector

arXiv 2112.01723 ↗First posted 3 Dec 2021cs.CV eess.IVcited by 11

Not on the map. Why?

Abstract (arXiv)

Data collected by Earth-observing (EO) satellites are often afflicted by cloud cover. Detecting the presence of clouds -- which is increasingly done using deep learning -- is crucial preprocessing in EO applications. In fact, advanced EO satellites perform deep learning-based cloud detection on board the satellites and downlink only clear-sky data to save precious bandwidth. In this paper, we highlight the vulnerability of deep learning-based cloud detection towards adversarial attacks. By optimising an adversarial pattern and superimposing it into a cloudless scene, we bias the neural network into detecting clouds in the scene. Since the input spectra of cloud detectors include the non-visible bands, we generated our attacks in the multispectral domain. This opens up the potential of multi-objective attacks, specifically, adversarial biasing in the cloud-sensitive bands and visual camouflage in the visible bands. We also investigated mitigation strategies against the adversarial attacks. We hope our work further builds awareness of the potential of adversarial attacks in the EO community.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 19 of its 70 references that are in the map. First posted on arXiv 3 Dec 2021.

Builds on

19 of 70 references.

References · 19

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  5. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  6. 2017Adversarial Patchcited by 514
  7. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  8. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 350
  9. 2019Fooling automated surveillance cameras: adversarial patches to attack person detectioncited by 268
  10. 2019Deep Learning for Hyperspectral Image Classification: An Overviewcited by 121
  11. 2017Robust Physical-World Attacks on Deep Learning Modelscited by 70
  12. 2021Physical Adversarial Attacks on an Aerial Imagery Object Detectorcited by 35
7 more
  1. 2017Using convolutional networks and satellite imagery to identify patterns in urban environments at a large scalecited by 23
  2. 2018Deep learning based cloud detection for medium and high resolution remote sensing images of different sensorscited by 20
  3. 2015Land Use Classification in Remote Sensing Images by Convolutional Neural Networkscited by 19
  4. 2018Adversarial Examples in Remote Sensingcited by 19
  5. 2018Cloud Detection Algorithm for Remote Sensing Images Using Fully Convolutional Neural Networkscited by 17
  6. 2020Adversarial Patch Camouflage against Aerial Detectioncited by 16
  7. 2021Automating Defense Against Adversarial Attacks: Discovery of Vulnerabilities and Application of Multi-INT Imagery to Protect Deployed Modelscited by 1

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 4; 2024: 3; 2025: 2.

11 papers.

  1. 2022Benchmarking Adversarial Patch Against Aerial Detectioncited by 21
  2. 2022Backdoor Attacks for Remote Sensing Data with Wavelet Transformcited by 6
  3. 2023A Comprehensive Study on the Robustness of Image Classification and Object Detection in Remote Sensing: Surveying and Benchmarkingcited by 5
  4. 2024Machine Learning in Space: Surveying the Robustness of on-board ML models to Radiationcited by 3
  5. 2023Quantifying the robustness of deep multispectral segmentation models against natural perturbations and data poisoningcited by 1
  6. 2023Domain Adaptation for Satellite-Borne Hyperspectral Cloud Detectioncited by 1
  7. 2024Adversarial Machine Learning Threats to Spacecraftcited by 1
  8. 2025First On-Orbit Demonstration of a Geospatial Foundation Modelcited by 1
  9. 2023Impact of architecture on robustness and interpretability of multispectral deep neural networkscited by 0
  10. 2024Texture- and Shape-based Adversarial Attacks for Overhead Image Vehicle Detectioncited by 0
  11. 2025Robust Physical Adversarial Patches Using Dynamically Optimized Clusterscited by 0