fu-bit Goto Github PK

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-examples-pytorch

Implementation of Papers on Adversarial Examples

adversarial-training-on-cifar10

In this repository we are going to create a robust network to Linfinity attacks using PGD optiminization

adversarial_cfiar10

CIFAR 10 ADVERSARIAL SAMPLES

adversarial_examples

对抗样本

auto-attack

Code relative to "Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks"

blackbox-attacks

Code used in 'Exploring the Space of Black-box Attacks on Deep Neural Networks' (https://arxiv.org/abs/1712.09491)

blackmagicdesign

Black Box Adversarial Attacks

cifar10_challenge

A challenge to explore adversarial robustness of neural networks on CIFAR10.

cnn_model

curls-whey

The implementation of 'Curls & Whey: Boosting Black-Box Adversarial Attacks' in pytorch

dast

A novel data-free model stealing method based on GAN

deepgcca-pytorch

An implementation of Deep Generalized Canonical Correlation Analysis (DGCCA or Deep GCCA) with pytorch.

denoisingnet_adversarial_training

PyTorch implementation of "Feature Denoising for Improving Adversarial Robustness" on CIFAR10.

ensemble_adversarial_attack

Ensemble Adversarial Black-Box Attacks against Deep Learning Systems Trained by MNIST, USPS and GTSRB Datasets

hybrid-artificial-potential-field-a-star-planning

This method takes best of both world. On one hand,it tries to reduce the overall path cost by using A-star and on other hand it reduces the time complexity by adapting real time reactive power from Artificial-Potential method of motion Planning.

linear-region-attack

A powerful white-box adversarial attack that exploits knowledge about the geometry of neural networks to find minimal adversarial perturbations without doing gradient descent

mocap-control

Realize inverse kinematics in mujoco through mocap control

nn_robust_attacks

Robust evasion attacks against neural network to find adversarial examples

pretrained-models.pytorch

Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.

prior-guided-rgf

procedural-advml

Task-agnostic Universal Black-box Attack on Computer Vision DNNs

pso

粒子群算法 matlab2016b

pso-pid

粒子群优化PID参数

pytorch-cifar100-adversarial-attack

coursework

pytorch-doc-zh

Pytorch 中文文档

resnet50-pytorch-face-recognition

Using Pytorch to implement a ResNet50 for Cross-Age Face Recognition

robotics-cooperative-path-planning-03-hybrid-a-star-trajectory-planning

Hybrid A Star Trajectory Planning in multi-vehicle cooperative planning in narrow free space.

simple-blackbox-attack

Code for ICML 2019 paper "Simple Black-box Adversarial Attacks"

simple_adversarial_examples

Repo of simple adversarial examples on vanilla neural networks trained on MNIST