mlsanityData to 7 Oct 2026

Out-of-Bounding-Box Triggers: A Stealthy Approach to Cheat Object Detectors

arXiv 2410.10091 ↗First posted 14 Oct 2024cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

In recent years, the study of adversarial robustness in object detection systems, particularly those based on deep neural networks (DNNs), has become a pivotal area of research. Traditional physical attacks targeting object detectors, such as adversarial patches and texture manipulations, directly manipulate the surface of the object. While these methods are effective, their overt manipulation of objects may draw attention in real-world applications. To address this, this paper introduces a more subtle approach: an inconspicuous adversarial trigger that operates outside the bounding boxes, rendering the object undetectable to the model. We further enhance this approach by proposing the Feature Guidance (FG) technique and the Universal Auto-PGD (UAPGD) optimization strategy for crafting high-quality triggers. The effectiveness of our method is validated through extensive empirical testing, demonstrating its high performance in both digital and physical environments. The code and video will be available at: https://github.com/linToTao/Out-of-bbox-attack.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 56 of its 72 references that are in the map. First posted on arXiv 14 Oct 2024.

Builds on

56 of 72 references.

References · 56

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  6. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  7. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  8. 2016Adversarial examples in the physical worldcited by 1,762
  9. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  10. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  11. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 968
  12. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
38 more
  1. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
  2. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 499
  3. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 459
  4. 2018SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networkscited by 445
  5. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 440
  6. 2019A Survey of Deep Learning Techniques for Autonomous Drivingcited by 401
  7. 2014Understanding Deep Image Representations by Inverting Themcited by 399
  8. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 328
  9. 2018Fast Online Object Tracking and Segmentation: A Unifying Approachcited by 272
  10. 2019Fooling automated surveillance cameras: adversarial patches to attack person detectioncited by 268
  11. 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 242
  12. 2015DeepDriving: Learning Affordance for Direct Perception in Autonomous Drivingcited by 229
  13. 2020Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNetscited by 165
  14. 2019RetinaFace: Single-stage Dense Face Localisation in the Wildcited by 164
  15. 2019Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Drivingcited by 151
  16. 2018DPatch: An Adversarial Patch Attack on Object Detectorscited by 146
  17. 2020Physically Realizable Adversarial Examples for LiDAR Object Detectioncited by 137
  18. 2021Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical Worldcited by 127
  19. 2020Adversarial Camouflage: Hiding Physical-World Attacks with Natural Stylescited by 126
  20. 2022Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenoncited by 101
  21. 2022Adversarial Texture for Fooling Person Detectors in the Physical Worldcited by 96
  22. 2019On Physical Adversarial Patches for Object Detectioncited by 93
  23. 2022Improving Adversarial Transferability via Neuron Attribution-Based Attackscited by 92
  24. 2019Universal Physical Camouflage Attacks on Object Detectorscited by 91
  25. 2022Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detectioncited by 79
  26. 2021FCA: Learning a 3D Full-coverage Vehicle Camouflage for Multi-view Physical Adversarial Attackcited by 74
  27. 2019Adversarial camera stickers: A physical camera-based attack on deep learning systemscited by 69
  28. 2020The Translucent Patch: A Physical and Universal Attack on Object Detectorscited by 62
  29. 2022Label-Only Model Inversion Attacks via Boundary Repulsioncited by 56
  30. 2021Fooling thermal infrared pedestrian detectors in real world using small bulbscited by 51
  31. 2020SLAP: Improving Physical Adversarial Examples with Short-Lived Adversarial Perturbationscited by 50
  32. 2022Enhancing Adversarial Training with Second-Order Statistics of Weightscited by 42
  33. 2022Adv-Attribute: Inconspicuous and Transferable Adversarial Attack on Face Recognitioncited by 42
  34. 2022Phantom Sponges: Exploiting Non-Maximum Suppression to Attack Deep Object Detectorscited by 28
  35. 2022SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretabilitycited by 28
  36. 2023Randomized Adversarial Training via Taylor Expansioncited by 28
  37. 2022Physical-World Optical Adversarial Attacks on 3D Face Recognitioncited by 23
  38. 2023RFLA: A Stealthy Reflected Light Adversarial Attack in the Physical Worldcited by 23

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025Enhancing Robust Fairness via Confusional Spectral Regularizationcited by 11
  2. 2025Beyond Vulnerabilities: A Survey of Adversarial Attacks as Both Threats and Defenses in Computer Vision Systemscited by 4
  3. 2026Transferable Physical-World Adversarial Patches Against Object Detection in Autonomous Drivingcited by 1