English

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

Computer Vision and Pattern Recognition 2021-09-02 v1

Abstract

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.

Keywords

Cite

@article{arxiv.2109.00224,
  title  = {A Protection Method of Trained CNN Model Using Feature Maps Transformed With Secret Key From Unauthorized Access},
  author = {MaungMaung AprilPyone and Hitoshi Kiya},
  journal= {arXiv preprint arXiv:2109.00224},
  year   = {2021}
}

Comments

To appear in APSIPA 2021. arXiv admin note: text overlap with arXiv:2105.14756