Pinned Repositories
ALCHEMY
A Language and Compiler for Homomorphic Encryption Made easY
autotest-cpp
Sample files for clang + gtest + cmake with on-write automated test
capnproto
Cap'n Proto serialization/RPC system - core tools and C++ library
cppcnn
CryptoNets
CryptoNets is a demonstration of the use of Neural-Networks over data encrypted with Homomorphic Encryption. Homomorphic Encryptions allow performing operations such as addition and multiplication over data while it is encrypted. Therefore, it allows keeping data private while outsourcing computation (see here and here for more about Homomorphic Encryptions and its applications). This project demonstrates the use of Homomorphic Encryption for outsourcing neural-network predictions. The scenario in mind is a provider that would like to provide Prediction as a Service (PaaS) but the data for which predictions are needed may be private. This may be the case in fields such as health or finance. By using CryptoNets, the user of the service can encrypt their data using Homomorphic Encryption and send only the encrypted message to the service provider. Since Homomorphic Encryptions allow the provider to operate on the data while it is encrypted, the provider can make predictions using a pre-trained Neural-Network while the data remains encrypted throughout the process and finaly send the prediction to the user who can decrypt the results. During the process the service provider does not learn anything about the data that was used, the prediction that was made or any intermediate result since everything is encrypted throughout the process. This project uses the Simple Encrypted Arithmetic Library SEAL version 3.2.1 implementation of Homomorphic Encryption developed in Microsoft Research.
DepthShrinker
[ICML 2022] "DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks", by Yonggan Fu, Haichuan Yang, Jiayi Yuan, Meng Li, Cheng Wan, Raghuraman Krishnamoorthi, Vikas Chandra, Yingyan Lin
dotconfig
configuration in ubuntu 18.04
dotfiles
@holman does dotfiles
dotfiles-1
:wrench: .files, including ~/.macos — sensible hacker defaults for macOS
e3
E3: Encrypt-Everything-Everywhere framework for compiling C++ programs with encrypted operands.
jyp4rk's Repositories
jyp4rk/ALCHEMY
A Language and Compiler for Homomorphic Encryption Made easY
jyp4rk/autotest-cpp
Sample files for clang + gtest + cmake with on-write automated test
jyp4rk/capnproto
Cap'n Proto serialization/RPC system - core tools and C++ library
jyp4rk/cppcnn
jyp4rk/CryptoNets
CryptoNets is a demonstration of the use of Neural-Networks over data encrypted with Homomorphic Encryption. Homomorphic Encryptions allow performing operations such as addition and multiplication over data while it is encrypted. Therefore, it allows keeping data private while outsourcing computation (see here and here for more about Homomorphic Encryptions and its applications). This project demonstrates the use of Homomorphic Encryption for outsourcing neural-network predictions. The scenario in mind is a provider that would like to provide Prediction as a Service (PaaS) but the data for which predictions are needed may be private. This may be the case in fields such as health or finance. By using CryptoNets, the user of the service can encrypt their data using Homomorphic Encryption and send only the encrypted message to the service provider. Since Homomorphic Encryptions allow the provider to operate on the data while it is encrypted, the provider can make predictions using a pre-trained Neural-Network while the data remains encrypted throughout the process and finaly send the prediction to the user who can decrypt the results. During the process the service provider does not learn anything about the data that was used, the prediction that was made or any intermediate result since everything is encrypted throughout the process. This project uses the Simple Encrypted Arithmetic Library SEAL version 3.2.1 implementation of Homomorphic Encryption developed in Microsoft Research.
jyp4rk/DepthShrinker
[ICML 2022] "DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks", by Yonggan Fu, Haichuan Yang, Jiayi Yuan, Meng Li, Cheng Wan, Raghuraman Krishnamoorthi, Vikas Chandra, Yingyan Lin
jyp4rk/dotconfig
configuration in ubuntu 18.04
jyp4rk/dotfiles
@holman does dotfiles
jyp4rk/dotfiles-1
:wrench: .files, including ~/.macos — sensible hacker defaults for macOS
jyp4rk/e3
E3: Encrypt-Everything-Everywhere framework for compiling C++ programs with encrypted operands.
jyp4rk/ezsh
quickly install zsh, oh-my-zsh with power-level-9k zsh-completions zsh-autosuggestions zsh-syntax-highlighting history-substring-search
jyp4rk/examples
Fast and flexible reference benchmarks
jyp4rk/fourier_neural_operator
Use Fourier transform to learn operators in differential equations.
jyp4rk/hernn
jyp4rk/histogram
jyp4rk/homepage_test
jyp4rk/jyp4rk.github.io
jyp4rk/MP-SPDZ
Versatile framework for multi-party computation
jyp4rk/openfhe-cuda
This is the development repository for the OpenFHE library. The current version is 1.0.3 (released on March 17, 2023).
jyp4rk/prezto
The configuration framework for Zsh
jyp4rk/private-join-and-compute
jyp4rk/SimKD
[CVPR-2022] Official implementation for "Knowledge Distillation with the Reused Teacher Classifier".
jyp4rk/stat_resnet18
jyp4rk/TenSEAL
A library for doing homomorphic encryption operations on tensors
jyp4rk/test_lattigo
jyp4rk/tf-encrypted
A Framework for Encrypted Machine Learning in TensorFlow
jyp4rk/zexe
Rust library for decentralized private computation