mlsanityData to 7 Oct 2026

Benchmarking Adversarial Patch Against Aerial Detection

arXiv 2210.16765 ↗First posted 30 Oct 2022cs.CVcited by 21

Not on the map. Why?

Abstract (arXiv)

DNNs are vulnerable to adversarial examples, which poses great security concerns for security-critical systems. In this paper, a novel adaptive-patch-based physical attack (AP-PA) framework is proposed, which aims to generate adversarial patches that are adaptive in both physical dynamics and varying scales, and by which the particular targets can be hidden from being detected. Furthermore, the adversarial patch is also gifted with attack effectiveness against all targets of the same class with a patch outside the target (No need to smear targeted objects) and robust enough in the physical world. In addition, a new loss is devised to consider more available information of detected objects to optimize the adversarial patch, which can significantly improve the patch's attack efficacy (Average precision drop up to 87.86% and 85.48% in white-box and black-box settings, respectively) and optimizing efficiency. We also establish one of the first comprehensive, coherent, and rigorous benchmarks to evaluate the attack efficacy of adversarial patches on aerial detection tasks. Finally, several proportionally scaled experiments are performed physically to demonstrate that the elaborated adversarial patches can successfully deceive aerial detection algorithms in dynamic physical circumstances. The code is available at https://github.com/JiaweiLian/AP-PA.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 43 of its 63 references that are in the map. First posted on arXiv 30 Oct 2022.

Builds on

43 of 63 references.

References · 43

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2013Intriguing properties of neural networkscited by 5,114
  8. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  9. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  10. 2018YOLOv3: An Incremental Improvementcited by 2,652
  11. 2016Adversarial examples in the physical worldcited by 1,762
  12. 2016YOLO9000: Better, Faster, Strongercited by 1,429
31 more
  1. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  2. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
  3. 2017DOTA: A Large-scale Dataset for Object Detection in Aerial Imagescited by 622
  4. 2017Adversarial Patchcited by 514
  5. 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
  6. 2019Fooling automated surveillance cameras: adversarial patches to attack person detectioncited by 268
  7. 2019Efficient Decision-based Black-box Adversarial Attacks on Face Recognitioncited by 173
  8. 2021On the Robustness of Vision Transformers to Adversarial Examplescited by 167
  9. 2018Physical Adversarial Examples for Object Detectorscited by 163
  10. 2019AdvHat: Real-world adversarial attack on ArcFace Face ID systemcited by 161
  11. 2019Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectorscited by 155
  12. 2020Adversarial Camouflage: Hiding Physical-World Attacks with Natural Stylescited by 126
  13. 2021Anchor-free Oriented Proposal Generator for Object Detectioncited by 104
  14. 2021Adversarial Sticker: A Stealthy Attack Method in the Physical Worldcited by 92
  15. 2017A General Framework for Adversarial Examples with Objectivescited by 82
  16. 2020The Translucent Patch: A Physical and Universal Attack on Object Detectorscited by 62
  17. 2018DARTS: Deceiving Autonomous Cars with Toxic Signscited by 53
  18. 2020Adversarial Light Projection Attacks on Face Recognition Systems: A Feasibility Studycited by 40
  19. 2019advPattern: Physical-World Attacks on Deep Person Re-Identification via Adversarially Transformable Patternscited by 35
  20. 2019On adversarial patches: real-world attack on ArcFace-100 face recognition systemcited by 35
  21. 2021Physical Adversarial Attacks on an Aerial Imagery Object Detectorcited by 35
  22. 2022Universal Adversarial Examples in Remote Sensing: Methodology and Benchmarkcited by 24
  23. 2018Adversarial Examples in Remote Sensingcited by 19
  24. 2022Zero-Query Transfer Attacks on Context-Aware Object Detectorscited by 17
  25. 2020Adversarial Patch Camouflage against Aerial Detectioncited by 16
  26. 2019Real-world adversarial attack on MTCNN face detection systemcited by 14
  27. 2022Towards Transferable Unrestricted Adversarial Examples with Minimum Changescited by 13
  28. 2021Adversarial Attacks against a Satellite-borne Multispectral Cloud Detectorcited by 11
  29. 2017Note on Attacking Object Detectors with Adversarial Stickerscited by 5
  30. 2020Simulating Unknown Target Models for Query-Efficient Black-box Attackscited by 5
  31. 2021Spectral Variability Augmented Sparse Unmixing of Hyperspectral Imagescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 5; 2025: 4; 2026: 6.

21 papers.

Sort:

By area:

  1. 2023Better Diffusion Models Further Improve Adversarial Trainingcited by 207
  2. 2023QKSAN: A Quantum Kernel Self-Attention Networkcited by 23
  3. 2025REOBench: Benchmarking Robustness of Earth Observation Foundation Modelscited by 13
  4. 2024Environmental Matching Attack Against Unmanned Aerial Vehicles Object Detectioncited by 11
  5. 2023Threatening Patch Attacks on Object Detection in Optical Remote Sensing Imagescited by 8
  6. 2023CBA: Contextual Background Attack against Optical Aerial Detection in the Physical Worldcited by 7
  7. 20253D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generationcited by 6
  8. 2023A Comprehensive Study on the Robustness of Image Classification and Object Detection in Remote Sensing: Surveying and Benchmarkingcited by 5
  9. 2025Beyond Vulnerabilities: A Survey of Adversarial Attacks as Both Threats and Defenses in Computer Vision Systemscited by 4
  10. 2024Attack Anything: Blind DNNs via Universal Background Adversarial Attackcited by 3
  11. 2023Contextual adversarial attack against aerial detection in the physical worldcited by 2
  12. 2024Model Agnostic Defense against Adversarial Patch Attacks on Object Detection in Unmanned Aerial Vehiclescited by 2
9 more
  1. 2024Cloud Adversarial Example Generation for Remote Sensing Image Classificationcited by 2
  2. 2025Learning Fourier shapes to probe the geometric world of deep neural networkscited by 1
  3. 2024PADetBench: Towards Benchmarking Physical Attacks against Object Detectioncited by 0
  4. 2026R-PGA: Robust Physical Adversarial Camouflage Generation via Relightable 3D Gaussian Splattingcited by 0
  5. 2026CAAP: Capture-Aware Adversarial Patch Attacks on Palmprint Recognition Modelscited by 0
  6. 2026AEGIS: A Semantic GAN and Evidential Learning Frameworkfor Robust Adversarial Detection in Vision Sensorscited by 0
  7. 2026ColorFD: A Finite-Difference Guided Black-Box Physical Adversarial Attack for Remote Sensing Object Detectioncited by 0
  8. 2026ARMOR: Manifold-Oriented Training for Adversarially Robust Aerial Object Detection under Data Scarcitycited by 0
  9. 2026Printability-Constrained Adversarial Decals for Near-Nadir Aerial Perception: Measured Ink Gamuts, Nested Realism Constraints, and a Physical-World Boundcited by 0