Zobrazeno 1 - 10
of 61
pro vyhledávání: '"Liew, Seng Pei"'
Autor:
Liu, Shang, Cao, Yang, Murakami, Takao, Liu, Weiran, Liew, Seng Pei, Takahashi, Tsubasa, Liu, Jinfei, Yoshikawa, Masatoshi
Collaborative graph analysis across multiple institutions is becoming increasingly popular. Realistic examples include social network analysis across various social platforms, financial transaction analysis across multiple banks, and analyzing the tr
Externí odkaz:
http://arxiv.org/abs/2405.20576
Applying Differentially Private Stochastic Gradient Descent (DPSGD) to training modern, large-scale neural networks such as transformer-based models is a challenging task, as the magnitude of noise added to the gradients at each iteration scales with
Externí odkaz:
http://arxiv.org/abs/2207.02699
Autor:
Liew, Seng Pei, Takahashi, Tsubasa
We study Gaussian mechanism in the shuffle model of differential privacy (DP). Particularly, we characterize the mechanism's R\'enyi differential privacy (RDP), showing that it is of the form: $$ \epsilon(\lambda) \leq \frac{1}{\lambda-1}\log\left(\f
Externí odkaz:
http://arxiv.org/abs/2206.09569
Local differential privacy (LDP) gives a strong privacy guarantee to be used in a distributed setting like federated learning (FL). LDP mechanisms in FL protect a client's gradient by randomizing it on the client; however, how can we interpret the pr
Externí odkaz:
http://arxiv.org/abs/2206.09122
We study a protocol for distributed computation called shuffled check-in, which achieves strong privacy guarantees without requiring any further trust assumptions beyond a trusted shuffler. Unlike most existing work, shuffled check-in allows clients
Externí odkaz:
http://arxiv.org/abs/2206.03151
Autor:
Liew, Seng Pei, Takahashi, Tsubasa, Takagi, Shun, Kato, Fumiyuki, Cao, Yang, Yoshikawa, Masatoshi
Recently, it is shown that shuffling can amplify the central differential privacy guarantees of data randomized with local differential privacy. Within this setup, a centralized, trusted shuffler is responsible for shuffling by keeping the identities
Externí odkaz:
http://arxiv.org/abs/2204.03919
Autor:
Kato, Fumiyuki, Takahashi, Tsubasa, Takagi, Shun, Cao, Yang, Liew, Seng Pei, Yoshikawa, Masatoshi
How can we explore the unknown properties of high-dimensional sensitive relational data while preserving privacy? We study how to construct an explorable privacy-preserving materialized view under differential privacy. No existing state-of-the-art me
Externí odkaz:
http://arxiv.org/abs/2203.06791
We assess the vulnerabilities of deep face recognition systems for images that falsify/spoof multiple identities simultaneously. We demonstrate that, by manipulating the deep feature representation extracted from a face image via imperceptibly small
Externí odkaz:
http://arxiv.org/abs/2110.00708
Publikováno v:
The Tenth International Conference on Learning Representations (ICLR 2022)
We propose a new framework of synthesizing data using deep generative models in a differentially private manner. Within our framework, sensitive data are sanitized with rigorous privacy guarantees in a one-shot fashion, such that training deep genera
Externí odkaz:
http://arxiv.org/abs/2106.04590
Autor:
Stakia, Anna, Dorigo, Tommaso, Banelli, Giovanni, Bortoletto, Daniela, Casa, Alessandro, de Castro, Pablo, Delaere, Christophe, Donini, Julien, Finos, Livio, Gallinaro, Michele, Giammanco, Andrea, Held, Alexander, Morales, Fabricio Jiménez, Kotkowski, Grzegorz, Liew, Seng Pei, Maltoni, Fabio, Menardi, Giovanna, Papavergou, Ioanna, Saggio, Alessia, Scarpa, Bruno, Strong, Giles C., Tosciri, Cecilia, Varela, João, Vischia, Pietro, Weiler, Andreas
Publikováno v:
Rev. Phys. 7 (2021) 100063
Between the years 2015 and 2019, members of the Horizon 2020-funded Innovative Training Network named "AMVA4NewPhysics" studied the customization and application of advanced multivariate analysis methods and statistical learning tools to high-energy
Externí odkaz:
http://arxiv.org/abs/2105.07530