Výsledky vyhledávání - "Hayashi, Naoto"

Report

Local Differential Privacy Image Generation Using Flow-based Deep Generative Models

Autor: Shibata, Hisaichi, Hanaoka, Shouhei, Cao, Yang, Yoshikawa, Masatoshi, Takenaga, Tomomi, Nomura, Yukihiro, Hayashi, Naoto, Abe, Osamu

Diagnostic radiologists need artificial intelligence (AI) for medical imaging, but access to medical images required for training in AI has become increasingly restrictive. To release and use medical images, we need an algorithm that can simultaneous

Externí odkaz: http://arxiv.org/abs/2212.10688

Zobrazit plný text záznamu

Report

Aging prediction using deep generative model toward the development of preventive medicine

Autor: Shibata, Hisaichi, Hanaoka, Shouhei, Nomura, Yukihiro, Hayashi, Naoto, Abe, Osamu

From birth to death, we all experience surprisingly ubiquitous changes over time due to aging. If we can predict aging in the digital domain, that is, the digital twin of the human body, we would be able to detect lesions in their very early stages,

Externí odkaz: http://arxiv.org/abs/2208.10797

Zobrazit plný text záznamu

Report

X2CT-FLOW: Maximum a posteriori reconstruction using a progressive flow-based deep generative model for ultra sparse-view computed tomography in ultra low-dose protocols

Autor: Shibata, Hisaichi, Hanaoka, Shouhei, Nomura, Yukihiro, Nakao, Takahiro, Takenaga, Tomomi, Hayashi, Naoto, Abe, Osamu

Ultra sparse-view computed tomography (CT) algorithms can reduce radiation exposure of patients, but those algorithms lack an explicit cycle consistency loss minimization and an explicit log-likelihood maximization in testing. Here, we propose X2CT-F

Externí odkaz: http://arxiv.org/abs/2104.04179

Zobrazit plný text záznamu

Report

KART: Parameterization of Privacy Leakage Scenarios from Pre-trained Language Models

Autor: Nakamura, Yuta, Hanaoka, Shouhei, Nomura, Yukihiro, Hayashi, Naoto, Abe, Osamu, Yada, Shuntaro, Wakamiya, Shoko, Aramaki, Eiji

For the safe sharing pre-trained language models, no guidelines exist at present owing to the difficulty in estimating the upper bound of the risk of privacy leakage. One problem is that previous studies have assessed the risk for different real-worl

Externí odkaz: http://arxiv.org/abs/2101.00036

Zobrazit plný text záznamu

Report

On the Matrix-Free Generation of Adversarial Perturbations for Black-Box Attacks

Autor: Shibata, Hisaichi, Hanaoka, Shouhei, Nomura, Yukihiro, Hayashi, Naoto, Abe, Osamu

In general, adversarial perturbations superimposed on inputs are realistic threats for a deep neural network (DNN). In this paper, we propose a practical generation method of such adversarial perturbation to be applied to black-box attacks that deman

Externí odkaz: http://arxiv.org/abs/2002.07317

Zobrazit plný text záznamu