6 papers
Shuffling-Aware Optimization for Private Vector Mean Estimation
Shun Takagi, Seng Pei Liew
We study -dimensional unbiased mean estimation in the single-message shuffle model, where each user sends a single privatized message and the analyzer only observes the shuffled…
DPSQL+: A Differentially Private SQL Library with a Minimum Frequency Rule
Tomoya Matsumoto, Shokichi Takakura, Shun Takagi +1
SQL is the de facto interface for exploratory data analysis; however, releasing exact query results can expose sensitive information through membership or attribute inference attac…
Analysis of Shuffling Beyond Pure Local Differential Privacy
Shun Takagi, Seng Pei Liew
Shuffling is a powerful way to amplify privacy of a local randomizer in private distributed data analysis. Most existing analyses of how shuffling amplifies privacy are based on th…
Securing Private Federated Learning in a Malicious Setting: A Scalable TEE-Based Approach with Client Auditing
Shun Takagi, Satoshi Hasegawa
In cross-device private federated learning, differentially private follow-the-regularized-leader (DP-FTRL) has emerged as a promising privacy-preserving method. However, existing a…
HRNet: Differentially Private Hierarchical and Multi-Resolution Network for Human Mobility Data Synthesization
Shun Takagi, Li Xiong, Fumiyuki Kato +2
Human mobility data offers valuable insights for many applications such as urban planning and pandemic response, but its use also raises privacy concerns. In this paper, we introdu…
ULDP-FL: Federated Learning with Across Silo User-Level Differential Privacy
Fumiyuki Kato, Li Xiong, Shun Takagi +2
Differentially Private Federated Learning (DP-FL) has garnered attention as a collaborative machine learning approach that ensures formal privacy. Most DP-FL approaches ensure DP a…