lingkok Goto Github PK

8num

A*算法求解八数码问题练习

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-detection-based-on-iacs

adversarial-detection-based-on-ied

adversarial-detection-based-on-ilacs

This is a method for detecting adversarial examples

adversarial-robustness-public

Code for AAAI 2018 accepted paper: "Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients"

adversarial-robustness-toolbox

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

adversarial-sample

生成神经网络对抗样本

adversarial_examples

对抗样本

adversaries_to_ood_detection

alae_tf2

This is a Python/Tensorflow 2.0 implementation of the Adversarial Latent AutoEncoders.

autoencoders_tf2.0

Simple, denoising and variational autoencoders made in TensorFlow2.0

contrastive_loss

Experiments with supervised contrastive learning methods with different loss functions

coupled-vae-improved-robustness-and-accuracy-of-a-variational-autoencoder

We present a coupled Variational Auto-Encoder (VAE) method that improves the accuracy and robustness of the probabilistic inferences on represented data. The new method models the dependency between input feature vectors (images) and weighs the outliers with a higher penalty by generalizing the original loss function to the coupled entropy function, using the principles of nonlinear statistical coupling. We evaluate the performance of the coupled VAE model using the MNIST dataset. Compared with the traditional VAE algorithm, the output images generated by the coupled VAE method are clearer and less blurry. The visualization of the input images embedded in 2D latent variable space provides a deeper insight into the structure of new model with coupled loss function: the latent variable has a smaller deviation and the output values are generated by a more compact latent space. We analyze the histograms of probabilities for the input images using the generalized mean metrics, in which increased geometric mean illustrates that the average likelihood of input data is improved. Increases in the -2/3 mean, which is sensitive to outliers, indicates improved robustness. The decisiveness, measured by the arithmetic mean of the likelihoods, is unchanged and -2/3 mean shows that the new model has better robustness.

deal-with-imagenet

decisiontree

ML，决策树算法笔记

deepsec

DEEPSEC: A Uniform Platform for Security Analysis of Deep Learning Model

detectors_review

draw_convnet

gan

VAE_GAN_WGAN_TF2.0

gans-collections-tf2.0_keras-eager_mode

This repository implements all kinds of GAN-models based on tensorflow2.0 keras API including GAN, CGAN, WGAN, WGAN_GP, VAE, CVAE, LSGAN, infoGAN, EBGAN, BEGAN, ACGAN

gnn_note

图神经网络整理

graphembedding

Implementation and experiments of graph embedding algorithms.

lid_adversarial_subspace_detection

Code for paper "Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality".

manifold

Implements of popular manifold algorithms in Python.

metapath2vec

nn_breaking_detection

Code corresponding to the paper "Adversarial Examples are not Easily Detected..."

nnif_adv_defense

Detection of adversarial examples using influence functions and nearest neighbors

ntu-reinforcementlearning-notes

国立**大学李宏毅老师讲解的深度强化学习学习笔记

odin

A simple and effective method for detecting out-of-distribution images in neural networks.