mlsanityData to 14 Oct 2026

Threatening Patch Attacks on Object Detection in Optical Remote Sensing Images

arXiv 2302.06060 ↗First posted 13 Feb 2023cs.CV cs.AI cs.CRcited by 8

Not on the map. Why?

Abstract (arXiv)

Advanced Patch Attacks (PAs) on object detection in natural images have pointed out the great safety vulnerability in methods based on deep neural networks. However, little attention has been paid to this topic in Optical Remote Sensing Images (O-RSIs). To this end, we focus on this research, i.e., PAs on object detection in O-RSIs, and propose a more Threatening PA without the scarification of the visual quality, dubbed TPA. Specifically, to address the problem of inconsistency between local and global landscapes in existing patch selection schemes, we propose leveraging the First-Order Difference (FOD) of the objective function before and after masking to select the sub-patches to be attacked. Further, considering the problem of gradient inundation when applying existing coordinate-based loss to PAs directly, we design an IoU-based objective function specific for PAs, dubbed Bounding box Drifting Loss (BDL), which pushes the detected bounding boxes far from the initial ones until there are no intersections between them. Finally, on two widely used benchmarks, i.e., DIOR and DOTA, comprehensive evaluations of our TPA with four typical detectors (Faster R-CNN, FCOS, RetinaNet, and YOLO-v4) witness its remarkable effectiveness. To the best of our knowledge, this is the first attempt to study the PAs on object detection in O-RSIs, and we hope this work can get our readers interested in studying this topic.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 43 of its 67 references that are in the map. First posted on arXiv 13 Feb 2023.

Builds on

43 of 67 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  7. 2013Intriguing properties of neural networkscited by 5,155
  8. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  9. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  10. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  11. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  12. 2016Adversarial examples in the physical worldcited by 1,769
31 more
  1. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,630
  2. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
  3. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,512
  4. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  5. 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
  6. 2017DOTA: A Large-scale Dataset for Object Detection in Aerial Imagescited by 623
  7. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 599
  8. 2017Adversarial Patchcited by 517
  9. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 462
  10. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 442
  11. 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 355
  12. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 333
  13. 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
  14. 2019Fooling automated surveillance cameras: adversarial patches to attack person detectioncited by 268
  15. 2018ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detectorcited by 159
  16. 2018DPatch: An Adversarial Patch Attack on Object Detectorscited by 147
  17. 2021Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical Worldcited by 127
  18. 2021Anchor-free Oriented Proposal Generator for Object Detectioncited by 105
  19. 2019On Physical Adversarial Patches for Object Detectioncited by 93
  20. 2020Opportunities and Challenges in Deep Learning Adversarial Robustness: A Surveycited by 72
  21. 2020DaST: Data-free Substitute Training for Adversarial Attackscited by 60
  22. 2018Guessing Smart: Biased Sampling for Efficient Black-Box Adversarial Attackscited by 46
  23. 2018Robust Adversarial Perturbation on Deep Proposal-based Modelscited by 26
  24. 2020Object Hider: Adversarial Patch Attack Against Object Detectorscited by 23
  25. 2022AI Security for Geoscience and Remote Sensing: Challenges and Future Trendscited by 23
  26. 2022Benchmarking Adversarial Patch Against Aerial Detectioncited by 21
  27. 2018Adversarial Examples in Remote Sensingcited by 19
  28. 2020DPAttack: Diffused Patch Attacks against Universal Object Detectioncited by 18
  29. 2021RPATTACK: Refined Patch Attack on General Object Detectorscited by 18
  30. 2020Adversarial Patch Camouflage against Aerial Detectioncited by 16
  31. 2020Pick-Object-Attack: Type-Specific Adversarial Attack for Object Detectioncited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 2; 2025: 1; 2026: 2.

8 papers.

  1. 2023Artificial intelligence to advance Earth observation: : A review of models, recent trends, and pathways forwardcited by 28
  2. 2023A Comprehensive Study on the Robustness of Image Classification and Object Detection in Remote Sensing: Surveying and Benchmarkingcited by 5
  3. 2024Beyond Grid Data: Exploring Graph Neural Networks for Earth Observationcited by 3
  4. 2024Cloud Adversarial Example Generation for Remote Sensing Image Classificationcited by 2
  5. 2025Towards Powerful and Practical Patch Attacks for 2D Object Detection in Autonomous Drivingcited by 1
  6. 2023Towards Generic and Controllable Attacks Against Object Detectioncited by 0
  7. 2026ColorFD: A Finite-Difference Guided Black-Box Physical Adversarial Attack for Remote Sensing Object Detectioncited by 0
  8. 2026Printability-Constrained Adversarial Decals for Near-Nadir Aerial Perception: Measured Ink Gamuts, Nested Realism Constraints, and a Physical-World Boundcited by 0