mlsanityData to 7 Oct 2026

Minority Reports Defense: Defending Against Adversarial Patches

arXiv 2004.13799 ↗First posted 28 Apr 2020cs.LG cs.CR cs.CVcited by 36

Not on the map. Why?

Abstract (arXiv)

Deep learning image classification is vulnerable to adversarial attack, even if the attacker changes just a small patch of the image. We propose a defense against patch attacks based on partially occluding the image around each candidate patch location, so that a few occlusions each completely hide the patch. We demonstrate on CIFAR-10, Fashion MNIST, and MNIST that our defense provides certified security against patch attacks of a certain size.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 9; 2023: 10; 2024: 4; 2025: 3; 2026: 1.

36 papers.

Sort:

By area:

  1. 2024Certifiably Robust RAG against Retrieval Corruptioncited by 144
  2. 2021Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detectioncited by 67
  3. 2021PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifiercited by 63
  4. 2023Detecting Backdoors in Pre-trained Encoderscited by 53
  5. 2021Harnessing Perceptual Adversarial Patches for Crowd Countingcited by 39
  6. 2023Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shiftcited by 31
  7. 2021PatchGuard++: Efficient Provable Attack Detection against Adversarial Patchescited by 29
  8. 2021DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding Attackscited by 28
  9. 2022ObjectSeeker: Certifiably Robust Object Detection against Patch Hiding Attacks via Patch-agnostic Maskingcited by 22
  10. 2021Adversarial YOLO: Defense Human Detection Patch Attacks via Detecting Adversarial Patchescited by 17
  11. 2022Adversarial Patch Attacks and Defences in Vision-Based Tasks: A Surveycited by 17
  12. 2022REAP: A Large-Scale Realistic Adversarial Patch Benchmarkcited by 17
24 more
  1. 2021ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layerscited by 15
  2. 2022Certified Defences Against Adversarial Patch Attacks on Semantic Segmentationcited by 15
  3. 2023BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defensecited by 15
  4. 2021Jujutsu: A Two-stage Defense against Adversarial Patch Attacks on Deep Neural Networkscited by 13
  5. 2024LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioningcited by 13
  6. 2022Backdoor Vulnerabilities in Normally Trained Deep Learning Modelscited by 12
  7. 2021PatchCensor: Patch Robustness Certification for Transformers via Exhaustive Testingcited by 11
  8. 2022Visual Adversarial Attacks and Defenses in the Physical World: A Surveycited by 11
  9. 2023PatchCURE: Improving Certifiable Robustness, Model Utility, and Computation Efficiency of Adversarial Patch Defensescited by 10
  10. 2023Adversarial Examples in the Physical World: A Surveycited by 10
  11. 2022Defending Person Detection Against Adversarial Patch Attack by using Universal Defensive Framecited by 9
  12. 2023Detection Defenses: An Empty Promise against Adversarial Patch Attacks on Optical Flowcited by 6
  13. 2022DECK: Model Hardening for Defending Pervasive Backdoorscited by 4
  14. 2022Real-Time Robust Video Object Detection System Against Physical-World Adversarial Attackscited by 3
  15. 2023PatchBackdoor: Backdoor Attack against Deep Neural Networks without Model Modificationcited by 3
  16. 2023Agnostic Multi-Robust Learning Using ERMcited by 2
  17. 2023A Majority Invariant Approach to Patch Robustness Certification for Deep Learning Modelscited by 1
  18. 2024CrossCert: A Cross-Checking Detection Approach to Patch Robustness Certification for Deep Learning Modelscited by 1
  19. 2025Concept-Based Masking: A Patch-Agnostic Defense Against Adversarial Patch Attackscited by 1
  20. 2023Assist Is Just as Important as the Goal: Image Resurfacing to Aid Model's Robust Predictioncited by 0
  21. 2024Redesigning Traffic Signs to Mitigate Machine-Learning Patch Attackscited by 0
  22. 2025SpaNN: Detecting Multiple Adversarial Patches on CNNs by Spanning Saliency Thresholdscited by 0
  23. 2025Scalable and Precise Patch Robustness Certification for Deep Learning Models with Top-k Predictionscited by 0
  24. 2026CertVLA: Certified Defense against Physical Visual Attacks for Vision-Language-Action Modelscited by 0