The increasing volume of personal and sensitive data being harvested by data controllers
makes it increasingly necessary to use the cloud not just to store the data, but also to …

Machine learning is widely used in practice to produce predictive models for applications
such as image processing, speech and text recognition. These models are more accurate …

We introduce CryptGPU, a system for privacy-preserving machine learning that implements
all operations on the GPU (graphics processing unit). Just as GPUs played a pivotal role in …

The growth of the Machine-Learning-As-A-Service (MLaaS) market has highlighted clients'
data privacy and security issues. Private inference (PI) techniques using cryptographic …

We propose a new notion of secure multiparty computation aided by a computationally-
powerful but untrusted" cloud" server. In this notion that we call on-the-fly multiparty …

Garbled circuits, a classical idea rooted in the work of Yao, have long been understood as a
cryptographic technique, not a cryptographic goal. Here we cull out a primitive …

Fully homomorphic encryption (FHE) enables secure computation over the encrypted data of
a single party. We explore how to extend this to multiple parties, using threshold fully …

In this paper, we propose a toolkit for efficient and privacy-preserving outsourced calculation
under multiple encrypted keys (EPOM). Using EPOM, a large scale of users can securely …

In recent years, signal processing applications that deal with user-related data have aroused
privacy concerns. For instance, face recognition and personalized recommendations rely on …

Secure Multi-Party Computation (MPC) allows mutually distrusting parties to run joint
computations without revealing private data. Current MPC algorithms scale poorly with data …