Delphi: A cryptographic inference system for neural networks

P Mishra, R Lehmkuhl, A Srinivasan, W Zheng… - Proceedings of the …, 2020 - dl.acm.org
Many companies provide neural network prediction services to users for a wide range of
applications. However, current prediction systems compromise one party's privacy: either the …

Low-complexity deep convolutional neural networks on fully homomorphic encryption using multiplexed parallel convolutions

E Lee, JW Lee, J Lee, YS Kim, Y Kim… - International …, 2022 - proceedings.mlr.press
Recently, the standard ResNet-20 network was successfully implemented on the fully
homomorphic encryption scheme, residue number system variant Cheon-Kim-Kim-Song …

CryptGPU: Fast privacy-preserving machine learning on the GPU

S Tan, B Knott, Y Tian, DJ Wu - 2021 IEEE Symposium on …, 2021 - ieeexplore.ieee.org
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 …

VeriFL: Communication-Efficient and Fast Verifiable Aggregation for Federated Learning

X Guo, Z Liu, J Li, J Gao, B Hou… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Federated learning (FL) enables a large number of clients to collaboratively train a global
model through sharing their gradients in each synchronized epoch of local training …

Cryptflow2: Practical 2-party secure inference

D Rathee, M Rathee, N Kumar, N Chandran… - Proceedings of the …, 2020 - dl.acm.org
We present CrypTFlow2, a cryptographic framework for secure inference over realistic Deep
Neural Networks (DNNs) using secure 2-party computation. CrypTFlow2 protocols are both …

Falcon: Honest-majority maliciously secure framework for private deep learning

S Wagh, S Tople, F Benhamouda, E Kushilevitz… - arxiv preprint arxiv …, 2020 - arxiv.org
We propose Falcon, an end-to-end 3-party protocol for efficient private training and
inference of large machine learning models. Falcon presents four main advantages-(i) It is …