Pinned Repositories
AdvBox
AdvBox是一款由百度安全实验室研发，在百度大范围使用的AI模型安全工具箱，目前原生支持PaddlePaddle、PyTorch、Caffe2、MxNet、Keras以及TensorFlow平台，方便广大开发者和安全工程师可以使用自己熟悉的框架。 AdvBox同时支持GraphPipe,屏蔽了底层使用的深度学习平台，用户可以通过几个命令就可以对PaddlePaddle、PyTorch、Caffe2、MxNet、CNTK、ScikitLearn以及TensorFlow平台生成的模型文件进行黑盒攻击。
adversarial-robustness-toolbox
This is a library dedicated to adversarial machine learning. Its purpose is to allow rapid crafting and analysis of attacks and defense methods for machine learning models. The Adversarial Robustness Toolbox provides an implementation for many state-of-the-art methods for attacking and defending classifiers. https://developer.ibm.com/code/open/projects/adversarial-robustness-toolbox/
attention
some attention implements
CIFAR10-CNN-Model
I built a Neural Network model with PyTorch library to recognize the CIFAR10 dataset, which consists of 10 different object images. Since PyTorch supports CIFAR10 dataset, accessing and loading of train and test images was easy.
mixup
Implementation of the mixup training method
mixup-cifar10
mixup: Beyond Empirical Risk Minimization
nn_robust_attacks
Robust evasion attacks against neural network to find adversarial examples
python-docs-samples
Code samples used on cloud.google.com
waveloc
Migration code for seismic event location
weitianli's Repositories
weitianli/AdvBox
AdvBox是一款由百度安全实验室研发，在百度大范围使用的AI模型安全工具箱，目前原生支持PaddlePaddle、PyTorch、Caffe2、MxNet、Keras以及TensorFlow平台，方便广大开发者和安全工程师可以使用自己熟悉的框架。 AdvBox同时支持GraphPipe,屏蔽了底层使用的深度学习平台，用户可以通过几个命令就可以对PaddlePaddle、PyTorch、Caffe2、MxNet、CNTK、ScikitLearn以及TensorFlow平台生成的模型文件进行黑盒攻击。
weitianli/adversarial-robustness-toolbox
This is a library dedicated to adversarial machine learning. Its purpose is to allow rapid crafting and analysis of attacks and defense methods for machine learning models. The Adversarial Robustness Toolbox provides an implementation for many state-of-the-art methods for attacking and defending classifiers. https://developer.ibm.com/code/open/projects/adversarial-robustness-toolbox/
weitianli/attention
some attention implements
weitianli/CIFAR10-CNN-Model
I built a Neural Network model with PyTorch library to recognize the CIFAR10 dataset, which consists of 10 different object images. Since PyTorch supports CIFAR10 dataset, accessing and loading of train and test images was easy.
weitianli/mixup
Implementation of the mixup training method
weitianli/mixup-cifar10
mixup: Beyond Empirical Risk Minimization
weitianli/nn_robust_attacks
Robust evasion attacks against neural network to find adversarial examples
weitianli/python-docs-samples
Code samples used on cloud.google.com
weitianli/waveloc
Migration code for seismic event location