mlsanityData to 7 Oct 2026

Block-wise Image Transformation with Secret Key for Adversarially Robust Defense

arXiv 2010.00801 ↗First posted 2 Oct 2020cs.CV cs.CRcited by 30

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a novel defensive transformation that enables us to maintain a high classification accuracy under the use of both clean images and adversarial examples for adversarially robust defense. The proposed transformation is a block-wise preprocessing technique with a secret key to input images. We developed three algorithms to realize the proposed transformation: Pixel Shuffling, Bit Flipping, and FFX Encryption. Experiments were carried out on the CIFAR-10 and ImageNet datasets by using both black-box and white-box attacks with various metrics including adaptive ones. The results show that the proposed defense achieves high accuracy close to that of using clean images even under adaptive attacks for the first time. In the best-case scenario, a model trained by using images transformed by FFX Encryption (block size of 4) yielded an accuracy of 92.30% on clean images and 91.48% under PGD attack with a noise distance of 8/255, which is close to the non-robust accuracy (95.45%) for the CIFAR-10 dataset, and it yielded an accuracy of 72.18% on clean images and 71.43% under the same attack, which is also close to the standard accuracy (73.70%) for the ImageNet dataset. Overall, all three proposed algorithms are demonstrated to outperform state-of-the-art defenses including adversarial training whether or not a model is under attack.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 12; 2023: 7; 2024: 1; 2025: 1; 2026: 2.

30 papers.

Sort:

By area:

  1. 2022An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applicationscited by 29
  2. 2022Privacy-Preserving Image Classification Using Isotropic Networkcited by 17
  3. 2021A Protection Method of Trained CNN Model with Secret Key from Unauthorized Accesscited by 15
  4. 2022Image and Model Transformation with Secret Key for Vision Transformercited by 12
  5. 2021Piracy-Resistant DNN Watermarking by Block-Wise Image Transformation with Secret Keycited by 9
  6. 2021A Protection Method of Trained CNN Model Using Feature Maps Transformed With Secret Key From Unauthorized Accesscited by 4
  7. 2021Access Control Using Spatially Invariant Permutation of Feature Maps for Semantic Segmentation Modelscited by 4
  8. 2022On the Transferability of Adversarial Examples between Encrypted Modelscited by 4
  9. 2023Generative Model-Based Attack on Learnable Image Encryption for Privacy-Preserving Deep Learningcited by 4
  10. 2023Enhanced Security against Adversarial Examples Using a Random Ensemble of Encrypted Vision Transformer Modelscited by 4
  11. 2022Access Control of Semantic Segmentation Models Using Encrypted Feature Mapscited by 3
  12. 2022Hindering Adversarial Attacks with Implicit Neural Representationscited by 3
18 more
  1. 2024Efficient Fine-Tuning with Domain Adaptation for Privacy-Preserving Vision Transformercited by 3
  2. 2023Hindering Adversarial Attacks with Multiple Encrypted Patch Embeddingscited by 2
  3. 2021Transfer Learning-Based Model Protection With Secret Keycited by 1
  4. 2022Towards Understanding and Harnessing the Effect of Image Transformation in Adversarial Detectioncited by 1
  5. 2022Access Control of Object Detection Models Using Encrypted Feature Mapscited by 1
  6. 2022Access Control with Encrypted Feature Maps for Object Detection Modelscited by 1
  7. 2023Advancing Adversarial Training by Injecting Booster Signalcited by 1
  8. 2023Domain Adaptation for Efficiently Fine-tuning Vision Transformer with Encrypted Imagescited by 1
  9. 2023Efficient Key-Based Adversarial Defense for ImageNet by Using Pre-trained Modelcited by 1
  10. 2025A Privacy-Preserving Semantic-Segmentation Method Using Domain-Adaptation Techniquecited by 1
  11. 2021Protecting Semantic Segmentation Models by Using Block-wise Image Encryption with Secret Key from Unauthorized Accesscited by 0
  12. 2021Protection of SVM Model with Secret Key from Unauthorized Accesscited by 0
  13. 2022Adversarial Detector with Robust Classifiercited by 0
  14. 2022An Encryption Method of ConvMixer Models without Performance Degradationcited by 0
  15. 2022On the Adversarial Transferability of ConvMixer Modelscited by 0
  16. 2023Adversarial Attacks Neutralization via Data Set Randomizationcited by 0
  17. 2026AdROD: HyperNetwork-based Adversarially Robust Object Detection for Autonomous Drivingcited by 0
  18. 2026Privacy-Preserving Object Detection for Vision Transformer-Based Modelscited by 0