mlsanityData to 7 Oct 2026

Towards Adversarially Robust Object Detection

arXiv 1907.10310 ↗First posted 24 Jul 2019cs.CV cs.LG eess.IVcited by 55

Not on the map. Why?

Abstract (arXiv)

Object detection is an important vision task and has emerged as an indispensable component in many vision system, rendering its robustness as an increasingly important performance factor for practical applications. While object detection models have been demonstrated to be vulnerable against adversarial attacks by many recent works, very few efforts have been devoted to improving their robustness. In this work, we take an initial attempt towards this direction. We first revisit and systematically analyze object detectors and many recently developed attacks from the perspective of model robustness. We then present a multi-task learning perspective of object detection and identify an asymmetric role of task losses. We further develop an adversarial training approach which can leverage the multiple sources of attacks for improving the robustness of detection models. Extensive experiments on PASCAL-VOC and MS-COCO verified the effectiveness of the proposed approach.

Key facts. Cited by 55 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 8; 2023: 12; 2024: 8; 2025: 5; 2026: 8.

55 papers.

Sort:

By area:

  1. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  2. 2021Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attackscited by 101
  3. 2021Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimizationcited by 75
  4. 2021Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detectioncited by 67
  5. 2023X-Adv: Physical Adversarial Object Attacks against X-ray Prohibited Item Detectioncited by 58
  6. 2021Robust and Accurate Object Detection via Adversarial Learningcited by 42
  7. 2023COCO-O: A Benchmark for Object Detectors under Natural Distribution Shiftscited by 34
  8. 2024PAD: Patch-Agnostic Defense against Adversarial Patch Attackscited by 31
  9. 2021DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding Attackscited by 28
  10. 2021Class-Aware Robust Adversarial Training for Object Detectioncited by 27
  11. 2022ObjectSeeker: Certifiably Robust Object Detection against Patch Hiding Attacks via Patch-agnostic Maskingcited by 22
  12. 2023Object Detection with Transformers: A Reviewcited by 22
38 more
  1. 2022Adversarial Attack and Defense of YOLO Detectors in Autonomous Driving Scenarioscited by 20
  2. 2022Does Robustness on ImageNet Transfer to Downstream Tasks?cited by 20
  3. 2022Adversarially-Aware Robust Object Detectorcited by 20
  4. 2023Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World Attackscited by 17
  5. 2023Identifying Label Errors in Object Detection Datasets by Loss Inspectioncited by 16
  6. 2021Towards Robust General Medical Image Segmentationcited by 14
  7. 2025Test-Time Backdoor Detection for Object Detection Modelscited by 14
  8. 2023On the Importance of Backbone to the Adversarial Robustness of Object Detectorscited by 12
  9. 2022Robust Real-World Image Super-Resolution against Adversarial Attackscited by 11
  10. 2021Generalized Real-World Super-Resolution through Adversarial Robustnesscited by 9
  11. 2021Natural Adversarial Objectscited by 7
  12. 2024A Survey and Evaluation of Adversarial Attacks for Object Detectioncited by 7
  13. 2021Sensor Adversarial Traits: Analyzing Robustness of 3D Object Detection Sensor Fusion Modelscited by 5
  14. 2023Robust Backdoor Attacks on Object Detection in Real Worldcited by 5
  15. 2024Self-supervised Adversarial Training of Monocular Depth Estimation against Physical-World Attackscited by 5
  16. 2021Consistent Semantic Attacks on Optical Flowcited by 4
  17. 2022Adaptive Adversarial Training to Improve Adversarial Robustness of DNNs for Medical Image Segmentation and Detectioncited by 4
  18. 2022General Adversarial Defense Against Black-box Attacks via Pixel Level and Feature Level Distribution Alignmentscited by 4
  19. 2024What Sketch Explainability Really Means for Downstream Taskscited by 4
  20. 2024Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patchescited by 4
  21. 2024Improving Domain Generalization in Self-supervised Monocular Depth Estimation via Stabilized Adversarial Trainingcited by 4
  22. 2021Robust and Accurate Object Detection via Self-Knowledge Distillationcited by 3
  23. 2024Can't Slow me Down: Learning Robust and Hardware-Adaptive Object Detectors against Latency Attacks for Edge Devicescited by 3
  24. 2025PBCAT: Patch-based composite adversarial training against physically realizable attacks on object detectioncited by 3
  25. 2021Adversarially Trained Object Detector for Unsupervised Domain Adaptationcited by 2
  26. 2023FROD: Robust Object Detection for Freecited by 2
  27. 2025Physical ID-Transfer Attacks against Multi-Object Tracking via Adversarial Trajectorycited by 2
  28. 2023Drawing the Same Bounding Box Twice? Coping Noisy Annotations in Object Detection with Repeated Labelscited by 1
  29. 2024SA-Attack: Speed-adaptive stealthy adversarial attack on trajectory predictioncited by 1
  30. 2025Reinforced Embodied Active Defense: Exploiting Adaptive Interaction for Robust Visual Perception in Adversarial 3D Environmentscited by 1
  31. 2025A Single Set of Adversarial Clothes Breaks Multiple Defense Methods in the Physical Worldcited by 1
  32. 2026Knowledge-Guided Adversarial Training for Infrared Object Detection via Thermal Radiation Modelingcited by 1
  33. 2022Optimizing One-pixel Black-box Adversarial Attackscited by 0
  34. 2023Towards Generic and Controllable Attacks Against Object Detectioncited by 0
  35. 2023CARNet: Collaborative Adversarial Resilience for Robust Underwater Image Enhancement and Perceptioncited by 0
  36. 2023Towards Improving Robustness Against Common Corruptions in Object Detectors Using Adversarial Contrastive Learningcited by 0
  37. 2026Control Your View: High-Resolution Global Semantic Manipulation in Learned Image Compressioncited by 0
  38. 2026LipSSD: Lipschitz-Constrained Single-Shot Detection for Adversarially Robust Object Detectioncited by 0

50 most cited of 55 All 55 (JSON)