PrivCirNet: Efficient Private Inference via Block Circulant Transformation
Homomorphic encryption (HE)-based deep neural network (DNN) inference protects data
and model privacy but suffers from significant computation overhead. We observe …
and model privacy but suffers from significant computation overhead. We observe …
Artemis: HE-Aware Training for Efficient Privacy-Preserving Machine Learning
Y Jeon, M Erez, M Orshansky - arXiv preprint arXiv:2310.01664, 2023 - arxiv.org
Privacy-Preserving ML (PPML) based on Homomorphic Encryption (HE) is a promising
foundational privacy technology. Making it more practical requires lowering its …
foundational privacy technology. Making it more practical requires lowering its …
Efficient privacy-preserving inference for convolutional neural networks
The processing of sensitive user data using deep learning models is an area that has
gained recent traction. Existing work has leveraged homomorphic encryption (HE) schemes …
gained recent traction. Existing work has leveraged homomorphic encryption (HE) schemes …
Orion: A Fully Homomorphic Encryption Compiler for Private Deep Neural Network Inference
Fully Homomorphic Encryption (FHE) has the potential to substantially improve privacy and
security by enabling computation on encrypted data. This is especially true with deep …
security by enabling computation on encrypted data. This is especially true with deep …
Cheetah: Optimizing and accelerating homomorphic encryption for private inference
As the application of deep learning continues to grow, so does the amount of data used to
make predictions. While traditionally big-data deep learning was constrained by computing …
make predictions. While traditionally big-data deep learning was constrained by computing …
Hyena: Optimizing Homomorphically Encrypted Convolution for Private CNN Inference
Processing convolution layers remains a huge bottleneck for private deep convolutional
neural network (CNN) inference for large datasets. To solve this issue, this paper presents a …
neural network (CNN) inference for large datasets. To solve this issue, this paper presents a …
Hyphen: A hybrid packing method and optimizations for homomorphic encryption-based neural network
J Park, D Kim, JH Ahn - 2023 - openreview.net
Private Inference (PI) enables users to enjoy secure AI inference services while companies
comply with regulations. Fully Homomorphic Encryption (FHE) based Convolutional Neural …
comply with regulations. Fully Homomorphic Encryption (FHE) based Convolutional Neural …
Optimizing layerwise polynomial approximation for efficient private inference on fully homomorphic encryption: a dynamic programming approach
Recent research has explored the implementation of privacy-preserving deep neural
networks solely using fully homomorphic encryption. However, its practicality has been …
networks solely using fully homomorphic encryption. However, its practicality has been …
He-pex: Efficient machine learning under homomorphic encryption using pruning, permutation and expansion
E Aharoni, M Baruch, P Bose… - arXiv preprint arXiv …, 2022 - arxiv.org
Privacy-preserving neural network (NN) inference solutions have recently gained significant
traction with several solutions that provide different latency-bandwidth trade-offs. Of these …
traction with several solutions that provide different latency-bandwidth trade-offs. Of these …
Sok: Privacy-preserving deep learning with homomorphic encryption
Outsourced computation for neural networks allows users access to state of the art models
without needing to invest in specialized hardware and know-how. The problem is that the …
without needing to invest in specialized hardware and know-how. The problem is that the …