mlsanityData to 14 Oct 2026

Universal Multi-view Black-box Attack against Object Detectors via Layout Optimization

arXiv 2407.06688 ↗First posted 9 Jul 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Object detectors have demonstrated vulnerability to adversarial examples crafted by small perturbations that can deceive the object detector. Existing adversarial attacks mainly focus on white-box attacks and are merely valid at a specific viewpoint, while the universal multi-view black-box attack is less explored, limiting their generalization in practice. In this paper, we propose a novel universal multi-view black-box attack against object detectors, which optimizes a universal adversarial UV texture constructed by multiple image stickers for a 3D object via the designed layout optimization algorithm. Specifically, we treat the placement of image stickers on the UV texture as a circle-based layout optimization problem, whose objective is to find the optimal circle layout filled with image stickers so that it can deceive the object detector under the multi-view scenario. To ensure reasonable placement of image stickers, two constraints are elaborately devised. To optimize the layout, we adopt the random search algorithm enhanced by the devised important-aware selection strategy to find the most appropriate image sticker for each circle from the image sticker pools. Extensive experiments conducted on four common object detectors suggested that the detection performance decreases by a large magnitude of 74.29% on average in multi-view scenarios. Additionally, a novel evaluation tool based on the photo-realistic simulator is designed to assess the texture-based attack fairly.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 44 of its 66 references that are in the map. First posted on arXiv 9 Jul 2024.

Builds on

44 of 66 references.

References · 44

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  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. 2020End-to-End Object Detection with Transformerscited by 7,414
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  6. 2017Mask R-CNNcited by 7,277
  7. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  8. 2013Intriguing properties of neural networkscited by 5,155
  9. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  10. 2016Adversarial Machine Learning at Scalecited by 936
  11. 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
  12. 2018Open3D: A Modern Library for 3D Data Processingcited by 721
32 more
  1. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
  2. 2017Countering Adversarial Images using Input Transformationscited by 520
  3. 2017Mitigating Adversarial Effects Through Randomizationcited by 383
  4. 2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
  5. 2018Feature Denoising for Improving Adversarial Robustnesscited by 314
  6. 2019Fooling automated surveillance cameras: adversarial patches to attack person detectioncited by 268
  7. 2018ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detectorcited by 159
  8. 2021Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical Worldcited by 127
  9. 2021Adversarial Sticker: A Stealthy Attack Method in the Physical Worldcited by 93
  10. 2019Universal Physical Camouflage Attacks on Object Detectorscited by 91
  11. 2018Generalizable Data-free Objective for Crafting Universal Adversarial Perturbationscited by 88
  12. 2018GenAttack: Practical Black-box Attacks with Gradient-Free Optimizationcited by 82
  13. 2021FCA: Learning a 3D Full-coverage Vehicle Camouflage for Multi-view Physical Adversarial Attackcited by 74
  14. 2020PatchAttack: A Black-box Texture-based Attack with Reinforcement Learningcited by 67
  15. 2017Fast Feature Fool: A data independent approach to universal adversarial perturbationscited by 66
  16. 2022DTA: Physical Camouflage Attacks using Differentiable Transformation Networkcited by 51
  17. 2022ViewFool: Evaluating the Robustness of Visual Recognition to Adversarial Viewpointscited by 48
  18. 2020Physical Adversarial Attack on Vehicle Detector in the Carla Simulatorcited by 38
  19. 2021TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systemscited by 36
  20. 2024PAD: Patch-Agnostic Defense against Adversarial Patch Attackscited by 32
  21. 2018Ask, Acquire, and Attack: Data-free UAP Generation using Class Impressionscited by 31
  22. 2022PatchZero: Defending against Adversarial Patch Attacks by Detecting and Zeroing the Patchcited by 30
  23. 2021Towards Robust Neural Image Compression: Adversarial Attack and Model Finetuningcited by 25
  24. 2022A Survey on Physical Adversarial Attack in Computer Visioncited by 25
  25. 2023RFLA: A Stealthy Reflected Light Adversarial Attack in the Physical Worldcited by 23
  26. 2021Learning Coated Adversarial Camouflages for Object Detectorscited by 17
  27. 2023Adversarial Attacks on Video Object Segmentation with Hard Region Discoverycited by 9
  28. 2020A Black-box Adversarial Attack Strategy with Adjustable Sparsity and Generalizability for Deep Image Classifierscited by 8
  29. 2020Black-box Adversarial Sample Generation Based on Differential Evolutioncited by 6
  30. 2021Improving the Transferability of Adversarial Examples with New Iteration Framework and Input Dropoutcited by 5
  31. 2022Dynamics-aware Adversarial Attack of Adaptive Neural Networkscited by 5
  32. 2023Efficient Search of Comprehensively Robust Neural Architectures via Multi-fidelity Evaluationcited by 2

Built on by

Not cited yet.