hzlg

Dubhe

Cradle

The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.

FLTrust_pytorch

FLAME

mentornet

Code for MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks

clean-net

Tensorflow source code for "CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise" (CVPR 2018)

Co-learning

The official implementation of the ACM MM'21 paper Co-learning: Learning from noisy labels with self-supervision.

coteaching_plus

ICML'19 How does Disagreement Help Generalization against Label Corruption?

inceptionv3-transferLearn-poison

Attacking a dog vs fish classification that uses transfer learning inceptionV3

SwanLab

⚡️SwanLab: your ML experiment notebook. 你的AI实验笔记本，跟踪与可视化你的机器学习全流程

friendly-noise

Code for Friendly Noise against Adversarial Noise: A Powerful Defense against Data Poisoning Attacks (NeurIPS 2022)

federated

A collection of Google research projects related to Federated Learning and Federated Analytics.

signSGD

Code for the signSGD paper

pytorch-cifar

95.47% on CIFAR10 with PyTorch

iclr2020_zeno_async

Source code of ICLR2020 submisstion: Zeno++: Robust Fully Asynchronous SGD

SignGuard

typora_plugin

Typora plugin. Feature enhancement tool | Typora 插件，功能增强工具

ups

"In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning" by Mamshad Nayeem Rizve, Kevin Duarte, Yogesh S Rawat, Mubarak Shah (ICLR 2021)

loss-landscape

Code for visualizing the loss landscape of neural nets

dlg

[NeurIPS 2019] Deep Leakage From Gradients

CollaborativeFairFederatedLearning

Official implementation of our work "Collaborative Fairness in Federated Learning."

gradient_descent_viz

interactive visualization of 5 popular gradient descent methods with step-by-step illustration and hyperparameter tuning UI

analysing_pii_leakage

The repository contains the code for analysing the leakage of personally identifiable (PII) information from the output of next word prediction language models.

security-paper

（与本人兴趣强相关的）各种安全or计算机资料收集

MAZE

Implementation of the paper "MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation".

cs-self-learning

计算机自学指南

mine-pytorch

Mutual Information Neural Estimation in Pytorch

Steal-ML

Model extraction attacks on Machine-Learning-as-a-Service platforms.

ML-Doctor

Code for ML Doctor

CSS-Inspiration

CSS Inspiration，在这里找到写 CSS 的灵感！