overgter,github

0_homomorphic-encryption-using-machine-learning

Homoporhic encryption provide you a safe encryption method that allows second party to process your encrypted data. No decryption is required so your data is safe

advbox

Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow and Advbox can benchmark the robustness of machine learning models. Advbox give a command line tool to generate adversarial examples with Zero-Coding.

adversarial-model-inversion

Code for "Neural Network Inversion in Adversarial Setting via Background Knowledge Alignment" (CCS 2019)

aispace2

Notebooks for learning AI.

amgecg_toolbox

Amang ECG Toolbox for MATLAB

arrhythmia-classification

Using machine learning technics for arrhythmia classification. Based on the MIT-BIH dataset and wfdb

arrhythmia-classification-1

biometrics

fingerprint recognition, etc.

capc-iclr

CaPC is a method that enables collaborating parties to improve their own local heterogeneous machine learning models in a setting where both confidentiality and privacy need to be preserved to prevent explicit and implicit sharing of private data.

cinc-challenge2017

ECG classification from short single lead segments (Computing in Cardiology Challenge 2017 entry)

cloudbrain

Platform for real-time wearables data analysis -- like EEG or ECG.

concrete-ml

Concrete-ML is a Privacy-Preserving Machine Learning (PPML) open-source set of tools which aims to simplify the use of fully homomorphic encryption (FHE) for data scientists. Particular care was given to the simplicity of our Python package in order to make it usable by any data scientist, even those without prior cryptography knowledge.

crimecamera

crypto

cryptography research, designs, and tools

dbd-for-finger-vein-recognition

This project is an algorithm for reproducing the paper《Discriminative Binary Descriptor for Finger Vein Recognition》，you can get the paper by https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8240902

deep-learning-for-ids

Using NSL_KDD data

differential-private-random-forest

This is an differential private version of Random forest. When any dataset, is used as a training dataset with this algorithm, it will not allow an adversary to disclose the sensitive information from the dataset.

differentially-private-federated-learning-with-homomorphic-encryption-mechanism

digit-recognition-using-h-elm

Implemented ELM and H-ELM algorithms and applied H-ELM on MNIST dataset for digit recognition

distributed-fuzzy-vault

Privacy mechanisms for decentralized fingerprint-based authentication

ebh

Prototype implementation for Encryption by Heart (EbH), a mechanism for symmetric key generation based on ElectroCardioGram (ECG) signals. This implementation is a contribution of paper: <details of the paper upon acceptance>