mlsanityData to 7 Oct 2026

Piracy-Resistant DNN Watermarking by Block-Wise Image Transformation with Secret Key

arXiv 2104.04241 ↗First posted 9 Apr 2021cs.CV cs.CR eess.IVcited by 9

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a novel DNN watermarking method that utilizes a learnable image transformation method with a secret key. The proposed method embeds a watermark pattern in a model by using learnable transformed images and allows us to remotely verify the ownership of the model. As a result, it is piracy-resistant, so the original watermark cannot be overwritten by a pirated watermark, and adding a new watermark decreases the model accuracy unlike most of the existing DNN watermarking methods. In addition, it does not require a special pre-defined training set or trigger set. We empirically evaluated the proposed method on the CIFAR-10 dataset. The results show that it was resilient against fine-tuning and pruning attacks while maintaining a high watermark-detection accuracy.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 27 of its 42 references that are in the map. First posted on arXiv 9 Apr 2021.

Builds on

27 of 42 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. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  5. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  6. 2017Mixed Precision Trainingcited by 1,135
  7. 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 334
  8. 2016EIE: Efficient Inference Engine on Compressed Deep Neural Networkcited by 291
  9. 2014Caffe: Convolutional Architecture for Fast Feature Embeddingcited by 287
  10. 2017Embedding Watermarks into Deep Neural Networkscited by 227
  11. 2017Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Ratescited by 196
  12. 2017Adversarial Frontier Stitching for Remote Neural Network Watermarkingcited by 110
15 more
  1. 2019[Extended version] Rethinking Deep Neural Network Ownership Verification: Embedding Passports to Defeat Ambiguity Attackscited by 82
  2. 2018Digital Watermarking for Deep Neural Networkscited by 37
  3. 2018Learnable Image Encryptioncited by 33
  4. 2018Encryption-then-Compression Systems using Grayscale-based Image Encryption for JPEG Imagescited by 33
  5. 2020Block-wise Image Transformation with Secret Key for Adversarially Robust Defensecited by 30
  6. 2020Block-wise Scrambled Image Recognition Using Adaptation Networkcited by 27
  7. 2020A GAN-Based Image Transformation Scheme for Privacy-Preserving Deep Neural Networkscited by 27
  8. 2018DeepMarks: A Digital Fingerprinting Framework for Deep Neural Networkscited by 23
  9. 2019Privacy-Preserving Deep Neural Networks with Pixel-based Image Encryption Considering Data Augmentation in the Encrypted Domaincited by 19
  10. 2021Robustness of on-device Models: Adversarial Attack to Deep Learning Models on Android Appscited by 19
  11. 2020Encryption Inspired Adversarial Defense for Visual Classificationcited by 17
  12. 2018DeepSigns: A Generic Watermarking Framework for IP Protection of Deep Learning Modelscited by 16
  13. 2020Training DNN Model with Secret Key for Model Protectioncited by 14
  14. 2020A Privacy-Preserving Machine Learning Scheme Using EtC Imagescited by 9
  15. 2020Image Transformation Network for Privacy-Preserving Deep Neural Networks and Its Security Evaluationcited by 8

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 5; 2023: 2; 2024: 1.

9 papers.

  1. 2022An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applicationscited by 29
  2. 2023Wide Flat Minimum Watermarking for Robust Ownership Verification of GANscited by 10
  3. 2021A Protection Method of Trained CNN Model Using Feature Maps Transformed With Secret Key From Unauthorized Accesscited by 4
  4. 2024DeepEclipse: How to Break White-Box DNN-Watermarking Schemescited by 4
  5. 2022Access Control of Semantic Segmentation Models Using Encrypted Feature Mapscited by 3
  6. 2022Access Control of Object Detection Models Using Encrypted Feature Mapscited by 1
  7. 2022Access Control with Encrypted Feature Maps for Object Detection Modelscited by 1
  8. 2022An Access Control Method with Secret Key for Semantic Segmentation Modelscited by 0
  9. 2023A Privacy Preserving Method with a Random Orthogonal Matrix for ConvMixer Modelscited by 0