Search Results for author: Tomoya Matsumoto

Found 2 papers, 1 papers with code

Privacy-Preserving Taxi-Demand Prediction Using Federated Learning

no code implementations14 May 2023 Yumeki Goto, Tomoya Matsumoto, Hamada Rizk, Naoto Yanai, Hirozumi Yamaguchi

Taxi-demand prediction is an important application of machine learning that enables taxi-providing facilities to optimize their operations and city planners to improve transportation infrastructure and services.

Federated Learning Privacy Preserving

Membership Inference Attacks against Diffusion Models

1 code implementation7 Feb 2023 Tomoya Matsumoto, Takayuki Miura, Naoto Yanai

We primarily discuss the diffusion model from the standpoints of comparison with a generative adversarial network (GAN) as conventional models and hyperparameters unique to the diffusion model, i. e., time steps, sampling steps, and sampling variances.

Generative Adversarial Network Inference Attack +1

Cannot find the paper you are looking for? You can Submit a new open access paper.