Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Shuffle Gaussian Mechanism for Differential Privacy



Seng Pei Liew , Tsubasa Takahashi

* The source code of our implementation is available at http://github.com/spliew/shuffgauss 

   Access Paper or Ask Questions

Shuffled Check-in: Privacy Amplification towards Practical Distributed Learning



Seng Pei Liew , Satoshi Hasegawa , Tsubasa Takahashi

* 16 pages, 4 figures 

   Access Paper or Ask Questions

Network Shuffling: Privacy Amplification via Random Walks



Seng Pei Liew , Tsubasa Takahashi , Shun Takagi , Fumiyuki Kato , Yang Cao , Masatoshi Yoshikawa

* 15 pages, 9 figures; SIGMOD 2022 version 

   Access Paper or Ask Questions

PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning



Seng Pei Liew , Tsubasa Takahashi , Michihiko Ueno

* 23 pages, 8 figures, 3 tables 

   Access Paper or Ask Questions

FaceLeaks: Inference Attacks against Transfer Learning Models via Black-box Queries



Seng Pei Liew , Tsubasa Takahashi


   Access Paper or Ask Questions

P3GM: Private High-Dimensional Data Release via Privacy Preserving Phased Generative Model



Shun Takagi , Tsubasa Takahashi , Yang Cao , Masatoshi Yoshikawa

* 12 pages 

   Access Paper or Ask Questions

Differentially Private Variational Autoencoders with Term-wise Gradient Aggregation



Tsubasa Takahashi , Shun Takagi , Hajime Ono , Tatsuya Komatsu

* 10 pages 

   Access Paper or Ask Questions

Indirect Adversarial Attacks via Poisoning Neighbors for Graph Convolutional Networks



Tsubasa Takahashi

* Accepted in IEEE BigData 2019 

   Access Paper or Ask Questions

Locally Private Distributed Reinforcement Learning



Hajime Ono , Tsubasa Takahashi


   Access Paper or Ask Questions

Lightweight Lipschitz Margin Training for Certified Defense against Adversarial Examples



Hajime Ono , Tsubasa Takahashi , Kazuya Kakizaki


   Access Paper or Ask Questions