mlsanityData to 14 Oct 2026

ObjectSeeker: Certifiably Robust Object Detection against Patch Hiding Attacks via Patch-agnostic Masking

arXiv 2202.01811 ↗First posted 3 Feb 2022cs.CVcited by 22

Not on the map. Why?

Abstract (arXiv)

Object detectors, which are widely deployed in security-critical systems such as autonomous vehicles, have been found vulnerable to patch hiding attacks. An attacker can use a single physically-realizable adversarial patch to make the object detector miss the detection of victim objects and undermine the functionality of object detection applications. In this paper, we propose ObjectSeeker for certifiably robust object detection against patch hiding attacks. The key insight in ObjectSeeker is patch-agnostic masking: we aim to mask out the entire adversarial patch without knowing the shape, size, and location of the patch. This masking operation neutralizes the adversarial effect and allows any vanilla object detector to safely detect objects on the masked images. Remarkably, we can evaluate ObjectSeeker's robustness in a certifiable manner: we develop a certification procedure to formally determine if ObjectSeeker can detect certain objects against any white-box adaptive attack within the threat model, achieving certifiable robustness. Our experiments demonstrate a significant (~10%-40% absolute and ~2-6x relative) improvement in certifiable robustness over the prior work, as well as high clean performance (~1% drop compared with undefended models).

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). Builds on 58 of its 90 references that are in the map. First posted on arXiv 3 Feb 2022.

Builds on

58 of 90 references.

References · 58

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  5. 2017Mask R-CNNcited by 7,277
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  7. 2013Intriguing properties of neural networkscited by 5,155
  8. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  9. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  10. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  11. 2018YOLOv3: An Incremental Improvementcited by 2,659
  12. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,630
38 more
  1. 2016YOLO9000: Better, Faster, Strongercited by 1,431
  2. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  3. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  4. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,020
  5. 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
  6. 2017Focal Loss for Dense Object Detectioncited by 752
  7. 2017Evasion Attacks against Machine Learning at Test Timecited by 689
  8. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 678
  9. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 567
  10. 2020On Adaptive Attacks to Adversarial Example Defensescited by 555
  11. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 546
  12. 2017Adversarial Patchcited by 517
  13. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 468
  14. 2019On Evaluating Adversarial Robustnesscited by 447
  15. 2019Provably Robust Deep Learning via Adversarially Trained Smoothed Classifierscited by 330
  16. 2018Certified Defenses against Adversarial Examplescited by 306
  17. 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 269
  18. 2019Fooling automated surveillance cameras: adversarial patches to attack person detectioncited by 268
  19. 2017On Detecting Adversarial Perturbationscited by 232
  20. 2018Physical Adversarial Examples for Object Detectorscited by 163
  21. 2018ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detectorcited by 159
  22. 2019Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectorscited by 155
  23. 2018DPatch: An Adversarial Patch Attack on Object Detectorscited by 147
  24. 2018Generating 3D Adversarial Point Cloudscited by 144
  25. 2018LaVAN: Localized and Visible Adversarial Noisecited by 113
  26. 2020Certified Defenses for Adversarial Patchescited by 101
  27. 2020(De)Randomized Smoothing for Certifiable Defense against Patch Attackscited by 98
  28. 2018Local Gradients Smoothing: Defense against localized adversarial attackscited by 87
  29. 2021You Only Learn One Representation: Unified Network for Multiple Taskscited by 86
  30. 2020PatchAttack: A Black-box Texture-based Attack with Reinforcement Learningcited by 67
  31. 2019Defending Against Physically Realizable Attacks on Image Classificationcited by 66
  32. 2021PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifiercited by 65
  33. 2019Towards Adversarially Robust Object Detectioncited by 55
  34. 2020Adversarial Training against Location-Optimized Adversarial Patchescited by 50
  35. 2021Certified Patch Robustness via Smoothed Vision Transformerscited by 45
  36. 2017Adversarial Examples that Fool Detectorscited by 40
  37. 2020Minority Reports Defense: Defending Against Adversarial Patchescited by 36
  38. 2021TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systemscited by 36

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 3; 2024: 4; 2025: 8; 2026: 2.

22 papers.

Sort:

By area:

  1. 2024Certifiably Robust RAG against Retrieval Corruptioncited by 151
  2. 2023Does Physical Adversarial Example Really Matter to Autonomous Driving? Towards System-Level Effect of Adversarial Object Evasion Attackcited by 37
  3. 2024PAD: Patch-Agnostic Defense against Adversarial Patch Attackscited by 32
  4. 2022Just Rotate it: Deploying Backdoor Attacks via Rotation Transformationcited by 20
  5. 2022REAP: A Large-Scale Realistic Adversarial Patch Benchmarkcited by 18
  6. 2022Certified Defences Against Adversarial Patch Attacks on Semantic Segmentationcited by 16
  7. 2023PatchCURE: Improving Certifiable Robustness, Model Utility, and Computation Efficiency of Adversarial Patch Defensescited by 11
  8. 2024ControlLoc: Physical-World Hijacking Attack on Visual Perception in Autonomous Drivingcited by 6
  9. 2024I Don't Know You, But I Can Catch You: Real-Time Defense against Diverse Adversarial Patches for Object Detectorscited by 5
  10. 2022Real-Time Robust Video Object Detection System Against Physical-World Adversarial Attackscited by 3
  11. 2025Revisiting Adversarial Patch Defenses on Object Detectors: Unified Evaluation, Large-Scale Dataset, and New Insightscited by 2
  12. 2025Online 3D Multi-Camera Perception through Robust 2D Tracking and Depth-based Late Aggregationcited by 2
10 more
  1. 2022Defending Object Detectors against Patch Attacks with Out-of-Distribution Smoothingcited by 1
  2. 2023Fight Fire with Fire: Combating Adversarial Patch Attacks using Pattern-randomized Defensive Patchescited by 1
  3. 2025A Survey of Adversarial Defenses in Vision-based Systems: Categorization, Methods and Challengescited by 1
  4. 2025From Pixels to Trajectory: Universal Adversarial Example Detection via Temporal Imprintscited by 1
  5. 2025PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patchescited by 1
  6. 2025Robustness Analysis against Adversarial Patch Attacks in Fully Unmanned Storescited by 0
  7. 2025SpaNN: Detecting Multiple Adversarial Patches on CNNs by Spanning Saliency Thresholdscited by 0
  8. 2025DisPatch: Disarming Adversarial Patches in Object Detection with Diffusion Modelscited by 0
  9. 2026AdROD: HyperNetwork-based Adversarially Robust Object Detection for Autonomous Drivingcited by 0
  10. 2026ARMOR: Manifold-Oriented Training for Adversarially Robust Aerial Object Detection under Data Scarcitycited by 0