mlsanityData to 7 Oct 2026

Breaking the Illusion: Real-world Challenges for Adversarial Patches in Object Detection

arXiv 2410.19863 ↗First posted 23 Oct 2024cs.CV cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Adversarial attacks pose a significant threat to the robustness and reliability of machine learning systems, particularly in computer vision applications. This study investigates the performance of adversarial patches for the YOLO object detection network in the physical world. Two attacks were tested: a patch designed to be placed anywhere within the scene - global patch, and another patch intended to partially overlap with specific object targeted for removal from detection - local patch. Various factors such as patch size, position, rotation, brightness, and hue were analyzed to understand their impact on the effectiveness of the adversarial patches. The results reveal a notable dependency on these parameters, highlighting the challenges in maintaining attack efficacy in real-world conditions. Learning to align digitally applied transformation parameters with those measured in the real world still results in up to a 64% discrepancy in patch performance. These findings underscore the importance of understanding environmental influences on adversarial attacks, which can inform the development of more robust defenses for practical machine learning applications.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 26 of its 35 references that are in the map. First posted on arXiv 23 Oct 2024.

Builds on

26 of 35 references.

References · 26

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  5. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  6. 2018YOLOv3: An Incremental Improvementcited by 2,652
  7. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
  8. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  9. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  10. 2019Fooling automated surveillance cameras: adversarial patches to attack person detectioncited by 268
  11. 2018ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detectorcited by 159
  12. 2023A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAScited by 149
14 more
  1. 2018DPatch: An Adversarial Patch Attack on Object Detectorscited by 146
  2. 2019On Physical Adversarial Patches for Object Detectioncited by 93
  3. 2021Adversarial Sticker: A Stealthy Attack Method in the Physical Worldcited by 92
  4. 2018Local Gradients Smoothing: Defense against localized adversarial attackscited by 85
  5. 2017Robust Physical-World Attacks on Deep Learning Modelscited by 70
  6. 2023How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defensescited by 65
  7. 2023YOLOv6 v3.0: A Full-Scale Reloadingcited by 58
  8. 2024PAD: Patch-Agnostic Defense against Adversarial Patch Attackscited by 31
  9. 2019APRICOT: A Dataset of Physical Adversarial Attacks on Object Detectioncited by 30
  10. 2022PatchZero: Defending against Adversarial Patch Attacks by Detecting and Zeroing the Patchcited by 30
  11. 2022Adversarial Attack and Defense of YOLO Detectors in Autonomous Driving Scenarioscited by 20
  12. 2023Detection Defenses: An Empty Promise against Adversarial Patch Attacks on Optical Flowcited by 6
  13. 2022Empirical Evaluation of Physical Adversarial Patch Attacks Against Overhead Object Detection Modelscited by 4
  14. 2023Geometric Data Augmentations to Mitigate Distribution Shifts in Pollen Classification from Microscopic Imagescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025Robust Physical Adversarial Patches Using Dynamically Optimized Clusterscited by 0
  2. 2025Adversarial Patch Attacks on Vision-Based Cargo Occupancy Estimation via Differentiable 3D Simulationcited by 0
  3. 2026Adversarial Patch Generation for Visual-Infrared Dense Prediction Tasks via Joint Position-Color Optimizationcited by 0
  4. 2026Street-Legal Physical-World Adversarial Rim for License Platescited by 0