no code implementations • 15 Feb 2022 • Hajime Ono, Kazuhiro Minami, Hideitsu Hino
Local differential privacy~(LDP) is an information-theoretic privacy definition suitable for statistical surveys that involve an untrusted data curator.
no code implementations • 19 Jun 2020 • Tsubasa Takahashi, Shun Takagi, Hajime Ono, Tatsuya Komatsu
This paper studies how to learn variational autoencoders with a variety of divergences under differential privacy constraints.
no code implementations • 31 Jan 2020 • Hajime Ono, Tsubasa Takahashi
To the best of our knowledge, this is the first work that actualizes distributed reinforcement learning under LDP.
no code implementations • 20 Nov 2018 • Hajime Ono, Tsubasa Takahashi, Kazuya Kakizaki
Lipschitz margin training (LMT) is a scalable certified defense, but it can also only achieve small robustness due to over-regularization.
no code implementations • COLING 2016 • Masayuki Asahara, Hajime Ono, Edson T. Miyamoto
The Dundee Eyetracking Corpus contains eyetracking data collected while native speakers of English and French read newspaper editorial articles.