mlsanityData to 14 Oct 2026

Detection as Regression: Certified Object Detection by Median Smoothing

arXiv 2007.03730 ↗First posted 7 Jul 2020cs.CV cs.CR cs.LGcited by 47

Not on the map. Why?

Abstract (arXiv)

Despite the vulnerability of object detectors to adversarial attacks, very few defenses are known to date. While adversarial training can improve the empirical robustness of image classifiers, a direct extension to object detection is very expensive. This work is motivated by recent progress on certified classification by randomized smoothing. We start by presenting a reduction from object detection to a regression problem. Then, to enable certified regression, where standard mean smoothing fails, we propose median smoothing, which is of independent interest. We obtain the first model-agnostic, training-free, and certified defense for object detection against ℓ2-bounded attacks. The code for all experiments in the paper is available at http://github.com/Ping-C/CertifiedObjectDetection .

Key facts. Cited by 47 papers in the map (data through 14 Oct 2026). First posted on arXiv 7 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 6; 2022: 10; 2023: 4; 2024: 14; 2025: 5; 2026: 8.

47 papers.

Sort:

By area:

  1. 2021Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detectioncited by 67
  2. 2022Planting Undetectable Backdoors in Machine Learning Modelscited by 59
  3. 2021Boosting Randomized Smoothing with Variance Reduced Classifierscited by 47
  4. 2021CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothingcited by 42
  5. 2022Certified Neural Network Watermarks with Randomized Smoothingcited by 41
  6. 2021Scalable Certified Segmentation via Randomized Smoothingcited by 35
  7. 2022PatchZero: Defending against Adversarial Patch Attacks by Detecting and Zeroing the Patchcited by 30
  8. 2021DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding Attackscited by 29
  9. 2022Double Sampling Randomized Smoothingcited by 22
  10. 2021Center Smoothing: Certified Robustness for Networks with Structured Outputscited by 18
  11. 2024Provably Unlearnable Data Examplescited by 18
  12. 2023Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networkscited by 16
35 more
  1. 2022Robust Probabilistic Time Series Forecastingcited by 15
  2. 2023Incremental Randomized Smoothing Certificationcited by 12
  3. 2022Private and Reliable Neural Network Inferencecited by 7
  4. 2022Invariance-Aware Randomized Smoothing Certificatescited by 7
  5. 2024Backdoor Attacks against Image-to-Image Networkscited by 7
  6. 2024A Survey and Evaluation of Adversarial Attacks for Object Detectioncited by 7
  7. 2024Certified Human Trajectory Predictioncited by 6
  8. 2022(De-)Randomized Smoothing for Decision Stump Ensemblescited by 5
  9. 2023A Certified Radius-Guided Attack Framework to Image Segmentation Modelscited by 5
  10. 2024Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality Metricscited by 5
  11. 2024RS-Reg: Probabilistic and Robust Certified Regression Through Randomized Smoothingcited by 4
  12. 2024Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agentscited by 4
  13. 2024Towards Formal Verification of Deep Neural Networks for Object Detectioncited by 4
  14. 2024Certifiably Robust Image Watermarkcited by 4
  15. 2024Adaptive Hierarchical Certification for Segmentation using Randomized Smoothingcited by 3
  16. 2025PBCAT: Patch-based composite adversarial training against physically realizable attacks on object detectioncited by 3
  17. 2022Multi-head Ensemble of Smoothed Classifiers for Certified Robustnesscited by 2
  18. 2024COMMIT: Certifying Robustness of Multi-Sensor Fusion Systems against Semantic Attackscited by 2
  19. 2025Reconcile Certified Robustness and Accuracy for DNN-based Smoothed Majority Vote Classifiercited by 2
  20. 2023Certified Robust Control under Adversarial Perturbationscited by 1
  21. 2024Universal Robustness via Median Randomized Smoothing for Real-World Super-Resolutioncited by 1
  22. 2024Effects of Exponential Gaussian Distribution on (Double Sampling) Randomized Smoothingcited by 1
  23. 2025Fast and Flexible Robustness Certificates for Semantic Segmentationcited by 1
  24. 2026Evaluating randomized smoothing as a defense against adversarial attacks in trajectory predictioncited by 1
  25. 2026Fortifying Time Series: DTW-Certified Robust Anomaly Detectioncited by 1
  26. 2022Certifying Safety in Reinforcement Learning under Adversarial Perturbation Attackscited by 0
  27. 2024Variational Randomized Smoothing for Sample-Wise Adversarial Robustnesscited by 0
  28. 2025Principal Eigenvalue Regularization for Improved Worst-Class Certified Robustness of Smoothed Classifierscited by 0
  29. 2025FS-IQA: Certified Feature Smoothing for Robust Image Quality Assessmentcited by 0
  30. 2026Feature-Space Smoothing: Certified Robustness of Deep Representationscited by 0
  31. 2026A Robust Out-of-Distribution Detection Framework via Synergistic Smoothingcited by 0
  32. 2026Self-Review Reinforcement Learning (SRRL) with Cross-Episode Memory and Policy Distillationcited by 0
  33. 2026LipSSD: Lipschitz-Constrained Single-Shot Detection for Adversarially Robust Object Detectioncited by 0
  34. 2026Clustered Randomized Smoothing for Stochastic Prediction Functionscited by 0
  35. 2026ARMOR: Manifold-Oriented Training for Adversarially Robust Aerial Object Detection under Data Scarcitycited by 0