mlsanityData to 7 Oct 2026

On the Importance of Backbone to the Adversarial Robustness of Object Detectors

arXiv 2305.17438 ↗First posted 27 May 2023cs.CV cs.AI cs.CRcited by 12

Not on the map. Why?

Abstract (arXiv)

Object detection is a critical component of various security-sensitive applications, such as autonomous driving and video surveillance. However, existing object detectors are vulnerable to adversarial attacks, which poses a significant challenge to their reliability and security. Through experiments, first, we found that existing works on improving the adversarial robustness of object detectors give a false sense of security. Second, we found that adversarially pre-trained backbone networks were essential for enhancing the adversarial robustness of object detectors. We then proposed a simple yet effective recipe for fast adversarial fine-tuning on object detectors with adversarially pre-trained backbones. Without any modifications to the structure of object detectors, our recipe achieved significantly better adversarial robustness than previous works. Finally, we explored the potential of different modern object detector designs for improving adversarial robustness with our recipe and demonstrated interesting findings, which inspired us to design state-of-the-art (SOTA) robust detectors. Our empirical results set a new milestone for adversarially robust object detection. Code and trained checkpoints are available at https://github.com/thu-ml/oddefense.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 53 of its 74 references that are in the map. First posted on arXiv 27 May 2023.

Builds on

53 of 74 references.

References · 53

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  8. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  9. 2017Mask R-CNNcited by 7,259
  10. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  11. 2013Intriguing properties of neural networkscited by 5,114
  12. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
38 more
  1. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  2. 2022A ConvNet for the 2020scited by 3,545
  3. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  4. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  6. 2018YOLOv3: An Incremental Improvementcited by 2,652
  7. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  8. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  9. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  10. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  11. 2018Panoptic Segmentationcited by 796
  12. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
  13. 2019Panoptic Feature Pyramid Networkscited by 644
  14. 2019Adversarial Training for Free!cited by 638
  15. 2018Do Better ImageNet Models Transfer Better?cited by 560
  16. 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
  17. 2022DN-DETR: Accelerate DETR Training by Introducing Query DeNoisingcited by 486
  18. 2019Cascade R-CNN: High Quality Object Detection and Instance Segmentationcited by 428
  19. 2021Conditional DETR for Fast Training Convergencecited by 422
  20. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 333
  21. 2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
  22. 2018Adversarially Robust Generalization Requires More Datacited by 318
  23. 2020Do Adversarially Robust ImageNet Models Transfer Better?cited by 315
  24. 2020Conditional Convolutions for Instance Segmentationcited by 314
  25. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 276
  26. 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
  27. 2021Improving Robustness using Generated Datacited by 233
  28. 2020Bag of Tricks for Adversarial Trainingcited by 199
  29. 2022Adversarial Texture for Fooling Person Detectors in the Physical Worldcited by 96
  30. 2023A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinkingcited by 85
  31. 2022Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detectioncited by 79
  32. 2021RobustART: Benchmarking Robustness on Architecture Design and Training Techniquescited by 78
  33. 2022A Light Recipe to Train Robust Vision Transformerscited by 64
  34. 2022When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecturecited by 64
  35. 2019Towards Adversarially Robust Object Detectioncited by 55
  36. 2021Fooling thermal infrared pedestrian detectors in real world using small bulbscited by 51
  37. 2021Class-Aware Robust Adversarial Training for Object Detectioncited by 27
  38. 2022Why Robust Generalization in Deep Learning is Difficult: Perspective of Expressive Powercited by 23

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 2; 2026: 6.

12 papers.

  1. 2024ADBM: Adversarial diffusion bridge model for reliable adversarial purificationcited by 24
  2. 2024Object Detectors in the Open Environment: Challenges, Solutions, and Outlookcited by 13
  3. 2024PartImageNet++ Dataset: Scaling up Part-based Models for Robust Recognitioncited by 7
  4. 2025PBCAT: Patch-based composite adversarial training against physically realizable attacks on object detectioncited by 3
  5. 2024TIMA: Text-Image Mutual Awareness for Balancing Zero-Shot Adversarial Robustness and Generalization Abilitycited by 2
  6. 2025A Single Set of Adversarial Clothes Breaks Multiple Defense Methods in the Physical Worldcited by 1
  7. 2026Generative Adversarial Perturbations with Cross-paradigm Transferability on Localized Crowd Countingcited by 1
  8. 2026PartImageNet++ Dataset: Enhancing Visual Models with High-Quality Part Annotationscited by 0
  9. 2026On the Adversarial Robustness of Discrete Image Tokenizerscited by 0
  10. 2026Complementary Text-Guided Attention for Zero-Shot Adversarial Robustnesscited by 0
  11. 2026Defending against Patch-Based and Texture-Based Adversarial Attacks with Spectral Decompositioncited by 0
  12. 2026LipSSD: Lipschitz-Constrained Single-Shot Detection for Adversarially Robust Object Detectioncited by 0