Min's Projects
Occlum is a memory-safe, multi-process library OS for Intel SGX
Benchmark datasets, data loaders, and evaluators for graph machine learning
A delightful community-driven (with 1,100+ contributors) framework for managing your zsh configuration. Includes 200+ optional plugins (rails, git, OSX, hub, capistrano, brew, ant, php, python, etc), over 140 themes to spice up your morning, and an auto-update tool so that makes it easy to keep up with the latest updates from the community.
Omniglot data set for one-shot learning
The one deep learning docker environment to rule them all.
Attacks using out-of-distribution adversarial examples
A repository in preparation for open-sourcing lottery ticket hypothesis code.
SDK for developing enclaves
An Open-Source Framework for Prompt-Learning.
Trusted side of the TEE
A hyperparameter optimization framework
os course info
Implementation of paper "Transferring Robustness for Graph Neural Network Against Poisoning Attacks".
Summaries of machine learning papers
Paddle Graph Learning (PGL) is an efficient and flexible graph learning framework based on PaddlePaddle
Latex code for making neural networks diagrams
BEST SCORE ON KAGGLE SO FAR , EVEN BETTER THAN THE KAGGLE TEAM MEMBER WHO DID BEST SO FAR. The project is about diagnosing pneumonia from XRay images of lungs of a person using self laid convolutional neural network and tranfer learning via inceptionV3. The images were of size greater than 1000 pixels per dimension and the total dataset was tagged large and had a space of 1GB+ . My work includes self laid neural network which was repeatedly tuned for one of the best hyperparameters and used variety of utility function of keras like callbacks for learning rate and checkpointing. Could have augmented the image data for even better modelling but was short of RAM on kaggle kernel. Other metrics like precision , recall and f1 score using confusion matrix were taken off special care. The other part included a brief introduction of transfer learning via InceptionV3 and was tuned entirely rather than partially after loading the inceptionv3 weights for the maximum achieved accuracy on kaggle till date. This achieved even a higher precision than before.
A unified benchmark problem for data poisoning attacks
How Powerful are Graph Neural Networks?
A simple and well styled PPO implementation. Based on my Medium series: https://medium.com/@eyyu/coding-ppo-from-scratch-with-pytorch-part-1-4-613dfc1b14c8.
A practical approach to learning machine learning.
AI实战-practicalAI 中文版
Strategies for Pre-training Graph Neural Networks
Library for training machine learning models with privacy for training data
Privacy Risks of Securing Machine Learning Models against Adversarial Examples
Privacy Engineering Collaboration Space
A toolbox for differentially private data generation
An implementation of the tools described in the paper entitled "Graphical-model based estimation and inference for differential privacy"
Implementation of the KDD 2020 paper "Graph Structure Learning for Robust Graph Neural Networks"
Model-independent universal black-box attack against computer vision DCNs.