A Protection Method of Trained CNN Model with Secret Key from Unauthorized Access
This addresses the issue of model security and copyright infringement for AI practitioners, though it is incremental as it builds on existing protection methods like passports.
The paper tackles the problem of unauthorized access to trained CNN models by proposing a protection method using a secret key set, which maintains model performance with the correct key but severely drops accuracy with incorrect keys, achieving close to non-protected model accuracy on CIFAR and ImageNet datasets.
In this paper, we propose a novel method for protecting convolutional neural network (CNN) models with a secret key set so that unauthorized users without the correct key set cannot access trained models. The method enables us to protect not only from copyright infringement but also the functionality of a model from unauthorized access without any noticeable overhead. We introduce three block-wise transformations with a secret key set to generate learnable transformed images: pixel shuffling, negative/positive transformation, and FFX encryption. Protected models are trained by using transformed images. The results of experiments with the CIFAR and ImageNet datasets show that the performance of a protected model was close to that of non-protected models when the key set was correct, while the accuracy severely dropped when an incorrect key set was given. The protected model was also demonstrated to be robust against various attacks. Compared with the state-of-the-art model protection with passports, the proposed method does not have any additional layers in the network, and therefore, there is no overhead during training and inference processes.