mlsanityData to 7 Oct 2026

Assist Is Just as Important as the Goal: Image Resurfacing to Aid Model's Robust Prediction

arXiv 2311.01563 ↗First posted 2 Nov 2023cs.CV cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

Adversarial patches threaten visual AI models in the real world. The number of patches in a patch attack is variable and determines the attack's potency in a specific environment. Most existing defenses assume a single patch in the scene, and the multiple patch scenarios are shown to overcome them. This paper presents a model-agnostic defense against patch attacks based on total variation for image resurfacing (TVR). The TVR is an image-cleansing method that processes images to remove probable adversarial regions. TVR can be utilized solely or augmented with a defended model, providing multi-level security for robust prediction. TVR nullifies the influence of patches in a single image scan with no prior assumption on the number of patches in the scene. We validate TVR on the ImageNet-Patch benchmark dataset and with real-world physical objects, demonstrating its ability to mitigate patch attack.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 43 references that are in the map. First posted on arXiv 2 Nov 2023.

Builds on

27 of 43 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  4. 2014Going Deeper with Convolutionscited by 4,231
  5. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
  6. 2017Countering Adversarial Images using Input Transformationscited by 517
  7. 2017Adversarial Patchcited by 514
  8. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  9. 2021Data Augmentation Can Improve Robustnesscited by 193
  10. 2018SentiNet: Detecting Localized Universal Attacks Against Deep Learning Systemscited by 148
  11. 2018DPatch: An Adversarial Patch Attack on Object Detectorscited by 146
  12. 2018LaVAN: Localized and Visible Adversarial Noisecited by 112
15 more
  1. 2020Certified Defenses for Adversarial Patchescited by 100
  2. 2020(De)Randomized Smoothing for Certifiable Defense against Patch Attackscited by 97
  3. 2018Local Gradients Smoothing: Defense against localized adversarial attackscited by 85
  4. 2022Physical Adversarial Attack meets Computer Vision: A Decade Surveycited by 66
  5. 2021PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifiercited by 63
  6. 2020Adversarial Training against Location-Optimized Adversarial Patchescited by 50
  7. 2021Certified Patch Robustness via Smoothed Vision Transformerscited by 44
  8. 2022Towards Practical Certifiable Patch Defense with Vision Transformercited by 44
  9. 2020Minority Reports Defense: Defending Against Adversarial Patchescited by 36
  10. 2021PatchGuard++: Efficient Provable Attack Detection against Adversarial Patchescited by 29
  11. 2022ImageNet-Patch: A Dataset for Benchmarking Machine Learning Robustness against Adversarial Patchescited by 27
  12. 2021Meta Adversarial Training against Universal Patchescited by 19
  13. 2022Adversarial Patch Attacks and Defences in Vision-Based Tasks: A Surveycited by 17
  14. 2020PatchGuard: A Provably Robust Defense against Adversarial Patches via Small Receptive Fields and Maskingcited by 13
  15. 2020Vax-a-Net: Training-time Defence Against Adversarial Patch Attackscited by 11

Built on by

Not cited yet.