[CVPR 2025 Highlight] Official code and models for Encoder-only Mask Transformer (EoMT).

Official implementation of the CVPR 2024 paper ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions.

Python library for adversarial machine learning, attacks and defences for neural networks, logistic regression, decision trees, SVM, gradient boosted trees, Gaussian processes and more with multipl…

A Toolbox for Adversarial Robustness Research

Reference models and tools for Cloud TPUs.

AI圈Noah plan-AI数据竞赛Top可复现解决方案(Awesome Top Solution List of Excellent AI Competitions)

Datasets, Transforms and Models specific to Computer Vision

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

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 mode…

Collections of all awesome thing!

A method for training neural networks that are provably robust to adversarial attacks.

Code for the CVPR 2019 article "Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defenses"

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

Code for "Black-box Adversarial Attacks with Limited Queries and Information" (http://arxiv.org/abs/1804.08598)

Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples

Basic Machine Learning and Deep Learning

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

Deflecting Adversarial Attacks with Pixel Deflection