Recently, the standard ResNet-20 network was successfully implemented on the fully
homomorphic encryption scheme, residue number system variant Cheon-Kim-Kim-Song …

Activation functions are crucial in deep learning networks, given that the nonlinear ability of
activation functions endows deep neural networks with real artificial intelligence. Nonlinear …

In two-party machine learning prediction services, the client's goal is to query a remote
server's trained machine learning model to perform neural network inference in some …

Secure inference of deep convolutional neural networks (CNNs) under RNS-CKKS involves
polynomial approximation of unsupported non-linear activation functions. However, existing …

Privacy and security have rapidly emerged as first order design constraints. Users now
demand more protection over who can see their data (confidentiality) as well as how it is …

Fully Homomorphic Encryption (FHE) enables computing on encrypted data, letting clients
securely offload computation to untrusted servers. While enticing, FHE has two key …

Homomorphic encryption is one of the main solutions for building secure and privacy-
preserving solutions for Machine Learning as a Service, a major challenge in a society …

Convolutional neural network (CNN) inference using fully homomorphic encryption (FHE) is
a promising private inference (PI) solution due to the capability of FHE that enables …

Fully homomorphic encryption (FHE) is a promising cryptographic primitive for realizing
private neural network inference (PI) services by allowing a client to fully offload the …

We propose an efficient non-interactive privacy-preserving Transformer inference
architecture called Powerformer. Since softmax is a non-algebraic operation, previous …