Federated learning (FL) is a machine learning setting where many clients (eg, mobile
devices or whole organizations) collaboratively train a model under the orchestration of a …

Two-party split learning is a popular technique for learning a model across feature-
partitioned data. In this work, we explore whether it is possible for one party to steal the …

Homomorphic encryption (HE)---the ability to perform computation on encrypted data---is an
attractive remedy to increasing concerns about data privacy in deep learning (DL). However …

Graph Neural Networks (GNNs) have demonstrated superior performance in learning node
representations for various graph inference tasks. However, learning over graph data can …

Federated learning (FL) protects training data in clients by collaboratively training local
machine learning models of clients for a global model, instead of directly feeding the training …

Privacy-preserving techniques allow private information to be used without compromising
privacy. Most encryption algorithms, such as the Advanced Encryption Standard (AES) …

Privacy-preserving deep learning with homomorphic encryption (HE) is a novel and
promising research area aimed at designing deep learning solutions that operate while …

Cloud storage allows organizations to store data at remote sites of service providers.
Although cloud storage services offer numerous benefits, they also involve new risks and …

A common privacy issue in traditional machine learning is that data needs to be disclosed
for the training procedures. In situations with highly sensitive data such as healthcare …

Encryption is the process of disguising text to ensure the confidentiality of data transmitted
from one party to another. Homomorphic encryption is one of the most important encryption …