mlsanityData to 7 Oct 2026

Towards Generic and Controllable Attacks Against Object Detection

arXiv 2307.12342 ↗First posted 23 Jul 2023cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Existing adversarial attacks against Object Detectors (ODs) suffer from two inherent limitations. Firstly, ODs have complicated meta-structure designs, hence most advanced attacks for ODs concentrate on attacking specific detector-intrinsic structures, which makes it hard for them to work on other detectors and motivates us to design a generic attack against ODs. Secondly, most works against ODs make Adversarial Examples (AEs) by generalizing image-level attacks from classification to detection, which brings redundant computations and perturbations in semantically meaningless areas (e.g., backgrounds) and leads to an emergency for seeking controllable attacks for ODs. To this end, we propose a generic white-box attack, LGP (local perturbations with adaptively global attacks), to blind mainstream object detectors with controllable perturbations. For a detector-agnostic attack, LGP tracks high-quality proposals and optimizes three heterogeneous losses simultaneously. In this way, we can fool the crucial components of ODs with a part of their outputs without the limitations of specific structures. Regarding controllability, we establish an object-wise constraint that exploits foreground-background separation adaptively to induce the attachment of perturbations to foregrounds. Experimentally, the proposed LGP successfully attacked sixteen state-of-the-art object detectors on MS-COCO and DOTA datasets, with promising imperceptibility and transferability obtained. Codes are publicly released in https://github.com/liguopeng0923/LGP.git

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 59 of its 74 references that are in the map. First posted on arXiv 23 Jul 2023.

Builds on

59 of 74 references.

References · 59

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  7. 2017Mask R-CNNcited by 7,259
  8. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  9. 2013Intriguing properties of neural networkscited by 5,114
  10. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  11. 2014Going Deeper with Convolutionscited by 4,231
  12. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
38 more
  1. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  2. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  3. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  4. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  5. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  6. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
  7. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  8. 2017One pixel attack for fooling deep neural networkscited by 579
  9. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 539
  10. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 494
  11. 2019Cascade R-CNN: High Quality Object Detection and Instance Segmentationcited by 428
  12. 2020Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detectioncited by 408
  13. 2022DiffusionDet: Diffusion Model for Object Detectioncited by 354
  14. 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
  15. 2019RepPoints: Point Set Representation for Object Detectioncited by 264
  16. 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 242
  17. 2020VarifocalNet: An IoU-aware Dense Object Detectorcited by 230
  18. 2021Oriented R-CNN for Object Detectioncited by 230
  19. 2020DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolutioncited by 222
  20. 2021TOOD: Task-aligned One-stage Object Detectioncited by 218
  21. 2021ReDet: A Rotation-equivariant Detector for Aerial Object Detectioncited by 202
  22. 2020Align Deep Features for Oriented Object Detectioncited by 186
  23. 2018DPatch: An Adversarial Patch Attack on Object Detectorscited by 146
  24. 2019Gliding vertex on the horizontal bounding box for multi-oriented object detectioncited by 134
  25. 2022MMRotate: A Rotated Object Detection Benchmark using PyTorchcited by 115
  26. 2018Transferable Adversarial Attacks for Image and Video Object Detectioncited by 109
  27. 2020AutoAssign: Differentiable Label Assignment for Dense Object Detectioncited by 100
  28. 2020On Success and Simplicity: A Second Look at Transferable Targeted Attackscited by 89
  29. 2022Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detectioncited by 79
  30. 2022Frequency-driven Imperceptible Adversarial Attack on Semantic Similaritycited by 76
  31. 2018On the Suitability of Lp-norms for Creating and Preventing Adversarial Examplescited by 57
  32. 2019Towards Adversarially Robust Object Detectioncited by 55
  33. 2022AO2-DETR: Arbitrary-Oriented Object Detection Transformercited by 55
  34. 2022A Large-scale Multiple-objective Method for Black-box Attack against Object Detectioncited by 55
  35. 2022Improving the Transferability of Targeted Adversarial Examples through Object-Based Diverse Inputcited by 49
  36. 2019Side-Aware Boundary Localization for More Precise Object Detectioncited by 36
  37. 2022Towards Understanding and Boosting Adversarial Transferability from a Distribution Perspectivecited by 36
  38. 2021Class-Aware Robust Adversarial Training for Object Detectioncited by 27

50 most cited of 59 All 59 (JSON)

Built on by

Not cited yet.