English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we propose a novel method for protecting convolutional neuralnetwork (CNN) models with a secret key set so that unauthorized users withoutthe correct key set cannot access trained models. The method enables us toprotect not only from copyright infringement but also the functionality of amodel from unauthorized access without any noticeable overhead. We introducethree block-wise transformations with a secret key set to generate learnabletransformed images: pixel shuffling, negative/positive transformation, and FFXencryption. Protected models are trained by using transformed images. Theresults of experiments with the CIFAR and ImageNet datasets show that theperformance of a protected model was close to that of non-protected models whenthe key set was correct, while the accuracy severely dropped when an incorrectkey set was given. The protected model was also demonstrated to be robustagainst various attacks. Compared with the state-of-the-art model protectionwith passports, the proposed method does not have any additional layers in thenetwork, and therefore, there is no overhead during training and inferenceprocesses.

A Protection Method of Trained CNN Model with Secret Key from Unauthorized Access