AriaNN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharing

Efficient Privacy Preserving Distributed Clustering Based on Secret Sharing

In this paper, we propose a privacy preserving distributed clustering protocol for horizontally partitioned data based on a very efficient homomorphic additive secret sharing scheme. The model we use for the protocol is novel in the sense that it utilizes two non-colluding third parties. We provide a brief security analysis of our protocol from information theoretic point of view, which is a st...

Privacy-preserving generative deep neural networks support clinical data sharing

Though it is widely recognized that data sharing enables faster scientific progress, the sensible need to protect participant privacy hampers this practice in medicine. We train deep neural networks that generate synthetic subjects closely resembling study participants. Using the SPRINT trial as an example, we show that machine-learning models built from simulated participants generalize to the...

Privacy Preserving Information Sharing

Privacy Preserving Aggregation of Secret Classifiers

In this paper, we address the issue of privacy preserving data-mining. Specifically, we consider a scenario where each member j of T parties has its own private database. The party j builds a private classifier hj for predicting a binary class variable y. The aim of this paper consists of aggregating these classifiers hj in order to improve individual predictions. More precisely, the parties wi...

Function Secret Sharing

Motivated by the goal of securely searching and updating distributed data, we introduce and study the notion of function secret sharing (FSS). This new notion is a natural generalization of distributed point functions (DPF), a primitive that was recently introduced by Gilboa and Ishai (Eurocrypt 2014). Given a positive integer p ≥ 2 and a class F of functions f : {0, 1} → G, where G is an Abeli...