Sanghyun-Hong

ZeroQ

[CVPR'20] ZeroQ: A Novel Zero Shot Quantization Framework

branchynet

DeepKNNDefense

KNN Defense Against Clean Label Poisoning Attacks

opacus

Training PyTorch models with differential privacy

Polaris

Code and data for NIPS'18 paper: Interpreting Neural Network Judgments via Minimal, Stable, and Symbolic Corrections

Gradient-Shaping

[Preprint] On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping

arxiv-latex-cleaner

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

fail

mia

A library for running membership inference attacks against ML models

EvaluatingDPML

This project's goal is to evaluate the privacy leakage of differentially private machine learning models.

dpml-benchmark

This repository contains the codes for first large-scale investigation of Differentially Private Convex Optimization algorithms.

Awesome-AutoDL

Automated Deep Learning: Neural Architecture Search Is Not the End (a curated list of AutoDL resources and an in-depth analysis)

slalom

Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware

portsmash

sgx-step

A practical attack framework for precise enclave execution control

conv_arithmetic

A technical report on convolution arithmetic in the context of deep learning

caffemodel2pytorch

Convert Caffe models to PyTorch

xlate

Code to evaluate XLATE attacks as well existing cache attacks.

pytorch-cnn-visualizations

Pytorch implementation of convolutional neural network visualization techniques

DeepRL

Modularized Implementation of Deep RL Algorithms in PyTorch

certml

Create certifiably secure scikit-learn compatible machine learning pipelines. Based on "Certified Defenses for Data Poisoning Attacks" by Steinhardt et al.

ganhacks

starter from "How to Train a GAN?" at NIPS2016

pytorch-playground

Base pretrained models and datasets in pytorch (MNIST, SVHN, CIFAR10, CIFAR100, STL10, AlexNet, VGG16, VGG19, ResNet, Inception, SqueezeNet)

vgg-faces-utils

Script to download and annotate images from VGG Faces dataset

adversarial-robustness-toolbox

Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

avclass

AVClass malware labeling tool

Pytorch-XNOR-Net

XNOR-Net, with binary gemm and binary conv2d kernels, support both CPU and GPU.

inceptionv3-transferLearn-poison

Attacking a dog vs fish classification that uses transfer learning inceptionV3

falco

Cloud Native Runtime Security

osquery

SQL powered operating system instrumentation, monitoring, and analytics.