mlsanityData to 7 Oct 2026

A Protection Method of Trained CNN Model Using Feature Maps Transformed With Secret Key From Unauthorized Access

arXiv 2109.00224 ↗First posted 1 Sep 2021cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a model protection method for convolutional neural networks (CNNs) with a secret key so that authorized users get a high classification accuracy, and unauthorized users get a low classification accuracy. The proposed method applies a block-wise transformation with a secret key to feature maps in the network. Conventional key-based model protection methods cannot maintain a high accuracy when a large key space is selected. In contrast, the proposed method not only maintains almost the same accuracy as non-protected accuracy, but also has a larger key space. Experiments were carried out on the CIFAR-10 dataset, and results show that the proposed model protection method outperformed the previous key-based model protection methods in terms of classification accuracy, key space, and robustness against key estimation attacks and fine-tuning attacks.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 18 of its 28 references that are in the map. First posted on arXiv 1 Sep 2021.

Builds on

18 of 28 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2013Intriguing properties of neural networkscited by 5,114
  3. 2017Mixed Precision Trainingcited by 1,135
  4. 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 334
  5. 2017Embedding Watermarks into Deep Neural Networkscited by 227
  6. 2017Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Ratescited by 196
  7. 2017Adversarial Frontier Stitching for Remote Neural Network Watermarkingcited by 110
  8. 2019[Extended version] Rethinking Deep Neural Network Ownership Verification: Embedding Passports to Defeat Ambiguity Attackscited by 82
  9. 2018Learnable Image Encryptioncited by 33
  10. 2018Encryption-then-Compression Systems using Grayscale-based Image Encryption for JPEG Imagescited by 33
  11. 2020Block-wise Image Transformation with Secret Key for Adversarially Robust Defensecited by 30
  12. 2018DeepMarks: A Digital Fingerprinting Framework for Deep Neural Networkscited by 23
6 more
  1. 2019Privacy-Preserving Deep Neural Networks with Pixel-based Image Encryption Considering Data Augmentation in the Encrypted Domaincited by 19
  2. 2018DeepSigns: A Generic Watermarking Framework for IP Protection of Deep Learning Modelscited by 16
  3. 2021A Protection Method of Trained CNN Model with Secret Key from Unauthorized Accesscited by 15
  4. 2020Training DNN Model with Secret Key for Model Protectioncited by 14
  5. 2020A Privacy-Preserving Machine Learning Scheme Using EtC Imagescited by 9
  6. 2021Piracy-Resistant DNN Watermarking by Block-Wise Image Transformation with Secret Keycited by 9

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 2.

4 papers.

  1. 2022An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applicationscited by 29
  2. 2023Enhanced Security against Adversarial Examples Using a Random Ensemble of Encrypted Vision Transformer Modelscited by 4
  3. 2023Turn Passive to Active: A Survey on Active Intellectual Property Protection of Deep Learning Modelscited by 2
  4. 2022Access Control of Object Detection Models Using Encrypted Feature Mapscited by 1