mlsanityData to 7 Oct 2026

MVPatch: More Vivid Patch for Adversarial Camouflaged Attacks on Object Detectors in the Physical World

arXiv 2312.17431 ↗First posted 29 Dec 2023cs.CR cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Recent studies have shown that Adversarial Patches (APs) can effectively manipulate object detection models. However, the conspicuous patterns often associated with these patches tend to attract human attention, posing a significant challenge. Existing research has primarily focused on enhancing attack efficacy in the physical domain while often neglecting the optimization of stealthiness and transferability. Furthermore, applying APs in real-world scenarios faces major challenges related to transferability, stealthiness, and practicality. To address these challenges, we introduce generalization theory into the context of APs, enabling our iterative process to simultaneously enhance transferability and refine visual correlation with realistic images. We propose a Dual-Perception-Based Framework (DPBF) to generate the More Vivid Patch (MVPatch), which enhances transferability, stealthiness, and practicality. The DPBF integrates two key components: the Model-Perception-Based Module (MPBM) and the Human-Perception-Based Module (HPBM), along with regularization terms. The MPBM employs ensemble strategy to reduce object confidence scores across multiple detectors, thereby improving AP transferability with robust theoretical support. Concurrently, the HPBM introduces a lightweight method for achieving visual similarity, creating natural and inconspicuous adversarial patches without relying on additional generative models. The regularization terms further enhance the practicality of the generated APs in the physical domain. Additionally, we introduce naturalness and transferability scores to provide an unbiased assessment of APs. Extensive experimental validation demonstrates that MVPatch achieves superior transferability and a natural appearance in both digital and physical domains, underscoring its effectiveness and stealthiness.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 49 of its 81 references that are in the map. First posted on arXiv 29 Dec 2023.

Builds on

49 of 81 references.

References · 49

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  7. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  8. 2015Fast R-CNNcited by 2,930
  9. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  10. 2016Adversarial examples in the physical worldcited by 1,762
  11. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  12. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
37 more
  1. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  2. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
  3. 2017One pixel attack for fooling deep neural networkscited by 579
  4. 2017Adversarial Patchcited by 514
  5. 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 352
  6. 2019Fooling automated surveillance cameras: adversarial patches to attack person detectioncited by 268
  7. 2018To understand deep learning we need to understand kernel learningcited by 186
  8. 2018Disentangling Adversarial Robustness and Generalizationcited by 171
  9. 2019AdvHat: Real-world adversarial attack on ArcFace Face ID systemcited by 161
  10. 2019Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectorscited by 155
  11. 2018DPatch: An Adversarial Patch Attack on Object Detectorscited by 146
  12. 2022Towards Adversarial Attack on Vision-Language Pre-training Modelscited by 142
  13. 2021Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical Worldcited by 127
  14. 2020Adversarial Camouflage: Hiding Physical-World Attacks with Natural Stylescited by 126
  15. 2023Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Modelscited by 106
  16. 2023AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learningcited by 101
  17. 2022Adversarial Texture for Fooling Person Detectors in the Physical Worldcited by 96
  18. 2019On Physical Adversarial Patches for Object Detectioncited by 93
  19. 2021Adversarial Sticker: A Stealthy Attack Method in the Physical Worldcited by 92
  20. 2019Universal Physical Camouflage Attacks on Object Detectorscited by 91
  21. 2021Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferabilitycited by 84
  22. 2021TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarioscited by 83
  23. 2023Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Modelscited by 79
  24. 2023Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllabilitycited by 66
  25. 2020Dense Attention Fluid Network for Salient Object Detection in Optical Remote Sensing Imagescited by 61
  26. 2022T-SEA: Transfer-based Self-Ensemble Attack on Object Detectioncited by 59
  27. 2017Video Salient Object Detection via Fully Convolutional Networkscited by 46
  28. 2019Universal Adversarial Perturbations for Speech Recognition Systemscited by 41
  29. 2022Simultaneously Optimizing Perturbations and Positions for Black-box Adversarial Patch Attackscited by 41
  30. 2023DAP: A Dynamic Adversarial Patch for Evading Person Detectorscited by 40
  31. 2021TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systemscited by 36
  32. 2020Stop-and-Go: Exploring Backdoor Attacks on Deep Reinforcement Learning-based Traffic Congestion Control Systemscited by 35
  33. 2023Query-Efficient Decision-based Black-Box Patch Attackcited by 19
  34. 2020Tracking-by-Counting: Using Network Flows on Crowd Density Maps for Tracking Multiple Targetscited by 18
  35. 2023AdvART: Adversarial Art for Camouflaged Object Detection Attackscited by 12
  36. 2023Adversarial Attacks on Video Object Segmentation with Hard Region Discoverycited by 9
  37. 2023Meta Generative Attack on Person Reidentificationcited by 5

Built on by

Cited by year

Citing papers per year: 2024: 3; 2025: 1.

4 papers.

  1. 2024Enhancing Object Detection Robustness: Detecting and Restoring Confidence in the Presence of Adversarial Patch Attackscited by 2
  2. 2024BEARD: Benchmarking the Adversarial Robustness for Dataset Distillationcited by 2
  3. 2024BACON: Bayesian Optimal Condensation Framework for Dataset Distillationcited by 1
  4. 2025Towards Powerful and Practical Patch Attacks for 2D Object Detection in Autonomous Drivingcited by 1