Training DNN Model with Secret Key for Model Protection
Not on the map. Why?
Abstract (arXiv)
In this paper, we propose a model protection method by using block-wise pixel shuffling with a secret key as a preprocessing technique to input images for the first time. The protected model is built by training with such preprocessed images. Experiment results show that the performance of the protected model is close to that of non-protected models when the key is correct, while the accuracy is severely dropped when an incorrect key is given, and the proposed model protection is robust against not only brute-force attacks but also fine-tuning attacks, while maintaining almost the same performance accuracy as that of using a non-protected model.
Key facts. Cited by 14 papers in the map (data through 13 Oct 2026). First posted on arXiv 6 Aug 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 8; 2022: 1; 2023: 2; 2024: 2; 2025: 1.
14 papers.
Sort:
By area:
- 2021A Protection Method of Trained CNN Model with Secret Key from Unauthorized Accesscited by 15
- 2024SLIP: Securing LLMs IP Using Weights Decompositioncited by 14
- 2021AdvParams: An Active DNN Intellectual Property Protection Technique via Adversarial Perturbation Based Parameter Encryptioncited by 13
- 2023Identifying Appropriate Intellectual Property Protection Mechanisms for Machine Learning Models: A Systematization of Watermarking, Fingerprinting, Model Access, and Attackscited by 12
- 2021Piracy-Resistant DNN Watermarking by Block-Wise Image Transformation with Secret Keycited by 10
- 2021Robust Black-box Watermarking for Deep NeuralNetwork using Inverse Document Frequencycited by 6
- 2025Re-Key-Free, Risky-Free: Adaptable Model Usage Controlcited by 6
- 2021A Protection Method of Trained CNN Model Using Feature Maps Transformed With Secret Key From Unauthorized Accesscited by 4
- 2021Access Control Using Spatially Invariant Permutation of Feature Maps for Semantic Segmentation Modelscited by 4
- 2023EncryIP: A Practical Encryption-Based Framework for Model Intellectual Property Protectioncited by 3
- 2024IDEA: An Inverse Domain Expert Adaptation Based Active DNN IP Protection Methodcited by 2
- 2021Transfer Learning-Based Model Protection With Secret Keycited by 1
- 2025Re-Key-Free, Risky-Free: Adaptable Model Usage Control24 Nov 2025
- 2024IDEA: An Inverse Domain Expert Adaptation Based Active DNN IP Protection Method29 Sep 2024
- 2024SLIP: Securing LLMs IP Using Weights Decomposition15 Jul 2024
- 2023EncryIP: A Practical Encryption-Based Framework for Model Intellectual Property Protection19 Dec 2023
- 2023Identifying Appropriate Intellectual Property Protection Mechanisms for Machine Learning Models: A Systematization of Watermarking, Fingerprinting, Model Access, and Attacks22 Apr 2023
- 2022Access Control with Encrypted Feature Maps for Object Detection Models29 Sep 2022
- 2021Access Control Using Spatially Invariant Permutation of Feature Maps for Semantic Segmentation Models3 Sep 2021
- 2021A Protection Method of Trained CNN Model Using Feature Maps Transformed With Secret Key From Unauthorized Access1 Sep 2021
- 2021Protecting Semantic Segmentation Models by Using Block-wise Image Encryption with Secret Key from Unauthorized Access20 Jul 2021
- 2021A Protection Method of Trained CNN Model with Secret Key from Unauthorized Access31 May 2021
- 2021AdvParams: An Active DNN Intellectual Property Protection Technique via Adversarial Perturbation Based Parameter Encryption28 May 2021
- 2021Piracy-Resistant DNN Watermarking by Block-Wise Image Transformation with Secret Key9 Apr 2021
- 2021AdvParams: An Active DNN Intellectual Property Protection Technique via Adversarial Perturbation Based Parameter Encryptioncited by 13
- 2023Identifying Appropriate Intellectual Property Protection Mechanisms for Machine Learning Models: A Systematization of Watermarking, Fingerprinting, Model Access, and Attackscited by 12
- 2023Identifying Appropriate Intellectual Property Protection Mechanisms for Machine Learning Models: A Systematization of Watermarking, Fingerprinting, Model Access, and Attacks22 Apr 2023
- 2021AdvParams: An Active DNN Intellectual Property Protection Technique via Adversarial Perturbation Based Parameter Encryption28 May 2021
- 2021A Protection Method of Trained CNN Model with Secret Key from Unauthorized Accesscited by 15
- 2024SLIP: Securing LLMs IP Using Weights Decompositioncited by 14
- 2021Piracy-Resistant DNN Watermarking by Block-Wise Image Transformation with Secret Keycited by 10
- 2021Robust Black-box Watermarking for Deep NeuralNetwork using Inverse Document Frequencycited by 6
- 2025Re-Key-Free, Risky-Free: Adaptable Model Usage Controlcited by 6
- 2021A Protection Method of Trained CNN Model Using Feature Maps Transformed With Secret Key From Unauthorized Accesscited by 4
- 2021Access Control Using Spatially Invariant Permutation of Feature Maps for Semantic Segmentation Modelscited by 4
- 2023EncryIP: A Practical Encryption-Based Framework for Model Intellectual Property Protectioncited by 3
- 2024IDEA: An Inverse Domain Expert Adaptation Based Active DNN IP Protection Methodcited by 2
- 2021Transfer Learning-Based Model Protection With Secret Keycited by 1
- 2022Access Control with Encrypted Feature Maps for Object Detection Modelscited by 1
- 2021Protecting Semantic Segmentation Models by Using Block-wise Image Encryption with Secret Key from Unauthorized Accesscited by 0
- 2025Re-Key-Free, Risky-Free: Adaptable Model Usage Control24 Nov 2025
- 2024IDEA: An Inverse Domain Expert Adaptation Based Active DNN IP Protection Method29 Sep 2024
- 2024SLIP: Securing LLMs IP Using Weights Decomposition15 Jul 2024
- 2023EncryIP: A Practical Encryption-Based Framework for Model Intellectual Property Protection19 Dec 2023
- 2022Access Control with Encrypted Feature Maps for Object Detection Models29 Sep 2022
- 2021Access Control Using Spatially Invariant Permutation of Feature Maps for Semantic Segmentation Models3 Sep 2021
- 2021A Protection Method of Trained CNN Model Using Feature Maps Transformed With Secret Key From Unauthorized Access1 Sep 2021
- 2021Protecting Semantic Segmentation Models by Using Block-wise Image Encryption with Secret Key from Unauthorized Access20 Jul 2021
- 2021A Protection Method of Trained CNN Model with Secret Key from Unauthorized Access31 May 2021
- 2021Piracy-Resistant DNN Watermarking by Block-Wise Image Transformation with Secret Key9 Apr 2021
- 2021Robust Black-box Watermarking for Deep NeuralNetwork using Inverse Document Frequency9 Mar 2021
- 2021Transfer Learning-Based Model Protection With Secret Key5 Mar 2021