Stars
《动手学深度学习》:面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.
ChatGPT 中文指南🔥,ChatGPT 中文调教指南,指令指南,应用开发指南,精选资源清单,更好的使用 chatGPT 让你的生产力 up up up! 🚀
Statistical learning methods, 统计学习方法(第2版)[李航] [笔记, 代码, notebook, 参考文献, Errata, lihang]
Base pretrained models and datasets in pytorch (MNIST, SVHN, CIFAR10, CIFAR100, STL10, AlexNet, VGG16, VGG19, ResNet, Inception, SqueezeNet)
PyTorch implementation of adversarial attacks [torchattacks]
基于TensorFlow训练的人脸识别神经网络
A challenge to explore adversarial robustness of neural networks on CIFAR10.
Code implementation of the paper "Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks", at IEEE Security and Privacy 2019.
VGG16 models for CIFAR-10 and CIFAR-100 using Keras
Simple PyTorch implementations of Badnets on MNIST and CIFAR10.
Practical Detection of Trojan Neural Networks
This repository contains a simple implementation of Interval Bound Propagation (IBP) using TensorFlow: https://arxiv.org/abs/1810.12715
Official Repository for the AAAI-20 paper "Hidden Trigger Backdoor Attacks"
Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching
Invisible Backdoor Attack with Sample-Specific Triggers
Code for "Label-Consistent Backdoor Attacks"
An Algorithm to Quantify Robustness of Recurrent Neural Networks
简单易用的接口管理解决方案,支持接口文档管理、Mock服务,接口测试等功能。接口文档采用 yaml 或 Excel 格式书写,简单快捷,Mock 基于该文档,无需数据库,一条命令秒变 Mock 服务。
[CVPR2020] Clean-Label Backdoor Attacks on Video Recognition Models
ATTA (Efficient Adversarial Training with Transferable Adversarial Examples)