Zobrazeno 1 - 10
of 79
pro vyhledávání: '"IIJIMA, RYOTA"'
Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs). In previous studies, the use of models encrypted with a secret key was demonstrated to be robust against white-box attacks, but not against black-box ones. In
Externí odkaz:
http://arxiv.org/abs/2402.07183
Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs). In addition, AEs have adversarial transferability, which means AEs generated for a source model can fool another black-box model (target model) with a non-triv
Externí odkaz:
http://arxiv.org/abs/2401.02633
We consider moral hazard problems where a principal has access to rich monitoring data about an agent's action. Rather than focusing on optimal contracts (which are known to in general be complicated), we characterize the optimal rate at which the pr
Externí odkaz:
http://arxiv.org/abs/2312.16789
This article presents block-wise image encryption for the vision transformer and its applications. Perceptual image encryption for deep learning enables us not only to protect the visual information of plain images but to also embed unique features c
Externí odkaz:
http://arxiv.org/abs/2308.07612
Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs). In addition, AEs have adversarial transferability, which means AEs generated for a source model can fool another black-box model (target model) with a non-triv
Externí odkaz:
http://arxiv.org/abs/2307.13985
Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs). In addition, AEs have adversarial transferability, which means AEs generated for a source model can fool another black-box model (target model) with a non-triv
Externí odkaz:
http://arxiv.org/abs/2209.08724
A novel method for access control with a secret key is proposed to protect models from unauthorized access in this paper. We focus on semantic segmentation models with the vision transformer (ViT), called segmentation transformer (SETR). Most existin
Externí odkaz:
http://arxiv.org/abs/2208.13135
Autor:
Iijima, Ryota, Kiya, Hitoshi
In this paper, we propose an encryption method for ConvMixer models with a secret key. Encryption methods for DNN models have been studied to achieve adversarial defense, model protection and privacy-preserving image classification. However, the use
Externí odkaz:
http://arxiv.org/abs/2207.11939
In this paper, we propose a combined use of transformed images and vision transformer (ViT) models transformed with a secret key. We show for the first time that models trained with plain images can be directly transformed to models trained with encr
Externí odkaz:
http://arxiv.org/abs/2207.05366
In this paper, we propose a block-wise image transformation method with a secret key for support vector machine (SVM) models. Models trained by using transformed images offer a poor performance to unauthorized users without a key, while they can offe
Externí odkaz:
http://arxiv.org/abs/2111.08927