Kunkun

Kunkun

CS & Applied Math & MPC @ GZU | Phd

A Review about Privacy-preserving Machine Learning

1 minute read

Published:

A basic protocol reference about privacy preserving machine learning.

ImprovementDerivation
OptimizationLow latency privacy preserving inference
 GAZELLE: A low latency framework for secure neural network inference
Matrix MultiplicationSecure outsourced matrix computation and application to neural networks
 More practical privacy- preserving machine learning as A service via efficient secure matrix multiplication
Non-linear FunctionImproved Primitives for MPC over Mixed Arithmetic-Binary Circuits
Linear FunctionnGraph-HE: a graph compiler for deep learning on homomorphically encrypted data
 CHET: an optimizing compiler for fully-homomorphic neural-network inferencing
 Privacy-preserving machine learning as a service
Binary FunctionQUOTIENT: Two-Party Secure Neural Network Training and Prediction
 XONN: XNOR-based oblivious deep neural network inference
Mixed crpto protocolSecure evaluation of quantized neural networks
 GAZELLE: A low latency framework for secure neural network inference
 Oblivious neural network predictions via minionn transformations
 SecureML: A system for scalable privacy-preserving machine learning
 ABY2.0: improved mixed-protocol secure two-party computation
 Slalom: Fast, verifiable and private execution of neural networks in trusted hardware
Non-HESecure evaluation of quantized neural networks
 Fantastic four: Honest-majority four-party secure computation with malicious security
 SWIFT: super-fast and robust privacy-preserving machine learning
 CrypT- Flow: Secure tensorflow inference
 ABY3: A Mixed Protocol Framework for Machine Learning
HEDELPHI: A cryptographic inference service for neural networks
 CrypTFlow2: Practical 2-party secure inference
 SortingHat: Efficient Private Decision Tree Evaluation via Homomorphic Encryption and Transciphering
RLHECheetah: Lean and Fast Secure Two-Party Deep Neural Network Inference

You May Also Enjoy