mlsanityData to 7 Oct 2026

Physical Adversarial Attacks on an Aerial Imagery Object Detector

arXiv 2108.11765 ↗First posted 26 Aug 2021cs.CVcited by 35

Not on the map. Why?

Abstract (arXiv)

Deep neural networks (DNNs) have become essential for processing the vast amounts of aerial imagery collected using earth-observing satellite platforms. However, DNNs are vulnerable towards adversarial examples, and it is expected that this weakness also plagues DNNs for aerial imagery. In this work, we demonstrate one of the first efforts on physical adversarial attacks on aerial imagery, whereby adversarial patches were optimised, fabricated and installed on or near target objects (cars) to significantly reduce the efficacy of an object detector applied on overhead images. Physical adversarial attacks on aerial images, particularly those captured from satellite platforms, are challenged by atmospheric factors (lighting, weather, seasons) and the distance between the observer and target. To investigate the effects of these challenges, we devised novel experiments and metrics to evaluate the efficacy of physical adversarial attacks against object detectors in aerial scenes. Our results indicate the palpable threat posed by physical adversarial attacks towards DNNs for processing satellite imagery.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Builds on 49 of its 72 references that are in the map. First posted on arXiv 26 Aug 2021.

Builds on

49 of 72 references.

References · 49

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  7. 2013Intriguing properties of neural networkscited by 5,114
  8. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  9. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  10. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  11. 2018YOLOv3: An Incremental Improvementcited by 2,652
  12. 2016Adversarial examples in the physical worldcited by 1,762
37 more
  1. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  2. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  3. 2016Adversarial Machine Learning at Scalecited by 934
  4. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  5. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  6. 2016Universal adversarial perturbationscited by 774
  7. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  8. 2017One pixel attack for fooling deep neural networkscited by 579
  9. 2017Adversarial Patchcited by 514
  10. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
  11. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 459
  12. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  13. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  14. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 350
  15. 2019Fooling automated surveillance cameras: adversarial patches to attack person detectioncited by 268
  16. 2018Adversarial Logit Pairingcited by 224
  17. 2018Physical Adversarial Examples for Object Detectorscited by 163
  18. 2019AdvHat: Real-world adversarial attack on ArcFace Face ID systemcited by 161
  19. 2018ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detectorcited by 159
  20. 2019Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectorscited by 155
  21. 2014Towards Deep Neural Network Architectures Robust to Adversarial Examplescited by 146
  22. 2021Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical Worldcited by 127
  23. 2019On Physical Adversarial Patches for Object Detectioncited by 93
  24. 2019Universal Physical Camouflage Attacks on Object Detectorscited by 91
  25. 2016A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learningcited by 86
  26. 2017Robust Physical-World Attacks on Deep Learning Modelscited by 70
  27. 2018The Effects of Super-Resolution on Object Detection Performance in Satellite Imagerycited by 57
  28. 2018DARTS: Deceiving Autonomous Cars with Toxic Signscited by 53
  29. 2017NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehiclescited by 48
  30. 2017MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examplescited by 46
  31. 2017Adversarial Examples that Fool Detectorscited by 39
  32. 2017Using convolutional networks and satellite imagery to identify patterns in urban environments at a large scalecited by 23
  33. 2018Adversarial Examples in Remote Sensingcited by 19
  34. 2020Adversarial Patch Camouflage against Aerial Detectioncited by 16
  35. 2018Rogue Signs: Deceiving Traffic Sign Recognition with Malicious Ads and Logoscited by 14
  36. 2020Satellite Image Classification with Deep Learningcited by 12
  37. 2017Note on Attacking Object Detectors with Adversarial Stickerscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 6; 2023: 6; 2024: 11; 2025: 5; 2026: 6.

35 papers.

Sort:

By area:

  1. 2024Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Roboticscited by 68
  2. 2022Physical Adversarial Attack meets Computer Vision: A Decade Surveycited by 66
  3. 2022A Survey on Physical Adversarial Attack in Computer Visioncited by 24
  4. 2025Eva-VLA: Evaluating Vision-Language-Action Models' Robustness Under Real-World Physical Variationscited by 24
  5. 2022Benchmarking Adversarial Patch Against Aerial Detectioncited by 21
  6. 2022The State of Aerial Surveillance: A Surveycited by 20
  7. 2021Adversarial Attacks against a Satellite-borne Multispectral Cloud Detectorcited by 11
  8. 2022Visual Adversarial Attacks and Defenses in the Physical World: A Surveycited by 11
  9. 2023Dynamic Adversarial Attacks on Autonomous Driving Systemscited by 11
  10. 2024Environmental Matching Attack Against Unmanned Aerial Vehicles Object Detectioncited by 11
  11. 2023Adversarial Examples in the Physical World: A Surveycited by 10
  12. 2023CBA: Contextual Background Attack against Optical Aerial Detection in the Physical Worldcited by 7
23 more
  1. 2022Transferable Physical Attack against Object Detection with Separable Attentioncited by 6
  2. 2023A Comprehensive Study on the Robustness of Image Classification and Object Detection in Remote Sensing: Surveying and Benchmarkingcited by 5
  3. 2025On Surjectivity of Neural Networks: Can you elicit any behavior from your model?cited by 4
  4. 2024Data-Driven Lipschitz Continuity: A Cost-Effective Approach to Improve Adversarial Robustnesscited by 3
  5. 2024Attack Anything: Blind DNNs via Universal Background Adversarial Attackcited by 3
  6. 2025PapMOT: Exploring Adversarial Patch Attack against Multiple Object Trackingcited by 3
  7. 2024Towards Non-Adversarial Algorithmic Recoursecited by 2
  8. 2024Model Agnostic Defense against Adversarial Patch Attacks on Object Detection in Unmanned Aerial Vehiclescited by 2
  9. 2024Adversarial Machine Learning Threats to Spacecraftcited by 1
  10. 2024Stealthy Multi-Task Adversarial Attackscited by 1
  11. 2024MAGIC: Mastering Physical Adversarial Generation in Context through Collaborative LLM Agentscited by 1
  12. 2024Distortion-Aware Adversarial Attacks on Bounding Boxes of Object Detectorscited by 1
  13. 2025Multimodal Large Language Models for Enhanced Traffic Safety: A Comprehensive Review and Future Trendscited by 1
  14. 2026Digital-to-Physical Transfer of Adversarial Patches for Aerial Vehicle Detectioncited by 1
  15. 2023Covert Communication Based on the Poisoning Attack in Federated Learningcited by 0
  16. 2023Eroding Trust In Aerial Imagery: Comprehensive Analysis and Evaluation Of Adversarial Attacks In Geospatial Systemscited by 0
  17. 2024Texture- and Shape-based Adversarial Attacks for Overhead Image Vehicle Detectioncited by 0
  18. 2025Robustness Analysis against Adversarial Patch Attacks in Fully Unmanned Storescited by 0
  19. 2026Towards Airborne Object Detection: A Deep Learning Analysiscited by 0
  20. 2026On the Adversarial Robustness of Remote Sensing Semantic Change Detectioncited by 0
  21. 2026ARMOR: Manifold-Oriented Training for Adversarially Robust Aerial Object Detection under Data Scarcitycited by 0
  22. 2026Physical Adversarial Examples for Person Detectors in Thermal Images Based on 3D Modelingcited by 0
  23. 2026Printability-Constrained Adversarial Decals for Near-Nadir Aerial Perception: Measured Ink Gamuts, Nested Realism Constraints, and a Physical-World Boundcited by 0