Low-complexity deep convolutional neural networks on fully homomorphic encryption using multiplexed parallel convolutions
Recently, the standard ResNet-20 network was successfully implemented on the fully
homomorphic encryption scheme, residue number system variant Cheon-Kim-Kim-Song …
homomorphic encryption scheme, residue number system variant Cheon-Kim-Kim-Song …
[HTML][HTML] Smish: A novel activation function for deep learning methods
X Wang, H Ren, A Wang - Electronics, 2022 - mdpi.com
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 …
activation functions endows deep neural networks with real artificial intelligence. Nonlinear …
Hyphen: A hybrid packing method and its optimizations for homomorphic encryption-based neural networks
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 …
a promising private inference (PI) solution due to the capability of FHE that enables …
A tensor compiler with automatic data packing for simple and efficient fully homomorphic encryption
Fully Homomorphic Encryption (FHE) enables computing on encrypted data, letting clients
securely offload computation to untrusted servers. While enticing, FHE has two key …
securely offload computation to untrusted servers. While enticing, FHE has two key …
Bitpacker: enabling high arithmetic efficiency in fully homomorphic encryption accelerators
Fully Homomorphic Encryption (FHE) enables computing directly on encrypted data. Though
FHE is slow on a CPU, recent hardware accelerators compensate most of FHE's overheads …
FHE is slow on a CPU, recent hardware accelerators compensate most of FHE's overheads …
Characterizing and optimizing end-to-end systems for private inference
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 …
server's trained machine learning model to perform neural network inference in some …
{AutoFHE}: Automated Adaption of {CNNs} for Efficient Evaluation over {FHE}
Secure inference of deep convolutional neural networks (CNNs) under RNS-CKKS involves
polynomial approximation of unsupported non-linear activation functions. However, existing …
polynomial approximation of unsupported non-linear activation functions. However, existing …
Fast and accurate homomorphic softmax evaluation
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 …
preserving solutions for Machine Learning as a Service, a major challenge in a society …
NeuJeans: Private Neural Network Inference with Joint Optimization of Convolution and FHE Bootstrap**
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 …
private neural network inference (PI) services by allowing a client to fully offload the …
HcLSH: A novel non-linear monotonic activation function for deep learning methods
Activation functions are essential components in any neural network model; they play a
crucial role in determining the network's expressive power through their introduced non …
crucial role in determining the network's expressive power through their introduced non …