Algorithms for outlier, adversarial and drift detection

《深度学习与计算机视觉》配套代码

An information security preparedness tool to do adversarial simulation.

Sentiment Analysis, Text Classification, Text Augmentation, Text Adversarial defense, etc.;

Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation

Backdoors Framework for Deep Learning and Federated Learning. A light-weight tool to conduct your research on backdoors.

Stochastic Adversarial Video Prediction

💡 Adversarial attacks on explanations and how to defend them

Adversarial Training for Natural Language Understanding

Crafting adversarial images

Adversarial Texture Optimization from RGB-D Scans (CVPR 2020).

Official TensorFlow Implementation of Adversarial Training for Free! which trains robust models at no extra cost compared to natural training.

Code and pretrained models for paper: Data-Free Adversarial Distillation

Code for ACL'2021 paper WARP 🌀 Word-level Adversarial ReProgramming. Outperforming `GPT-3` on SuperGLUE Few-Shot text classification. https://aclanthology.org/2021.acl-long.381/

A PyTorch implementation of adversarial pose estimation for multi-person

[Nature Machine Intelligence Journal] Official pytorch implementation for Uncertainty-Guided Dual-Views for Semi-Supervised Volumetric Medical Image Segmentation

A checkers reinforcement learning AI, and all the tools needed to train it.

RayS: A Ray Searching Method for Hard-label Adversarial Attack (KDD2020)

Torch implementation of various types of GAN (e.g. DCGAN, ALI, Context-encoder, DiscoGAN, CycleGAN, EBGAN, LSGAN)

Implementation of adversarial training under fast-gradient sign method (FGSM), projected gradient descent (PGD) and CW using Wide-ResNet-28-10 on cifar-10. Sample code is re-usable despite changing the model or dataset.