In this paper, we propose a combined use of transformed images and visio...
Deep neural network (DNN) models are wellknown to easily misclassify
pre...
In this paper, we propose an access control method that uses the spatial...
In this paper, we propose a model protection method for convolutional ne...
Since production-level trained deep neural networks (DNNs) are of a grea...
In this paper, we propose a novel DNN watermarking method that utilizes ...
We propose a novel method for protecting trained models with a secret ke...
We propose a voting ensemble of models trained by using block-wise
trans...
In this paper, we propose a novel defensive transformation that enables ...
In this paper, we propose a model protection method by using block-wise ...
Conventional adversarial defenses reduce classification accuracy whether...
Data for deep learning should be protected for privacy preserving.
Resea...