Code for the prototype tool in our paper "CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data Poisoning".

Last update: Oct 26, 2021

Related tags

Deep Learning CoProtector

Overview

CoProtector

Code for the prototype tool in our paper "CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data Poisoning".

Install

The tool requires Python3.6+.

The depandences in the following are used:

tree-sitter               0.19.0
pygithub                  1.55 
nltk                      3.5

Usage

Edit config.py following the instruction in README, and run:

python run.py

Config

Property	Example	Introdution
language	'java'	As a prototype tool, CoProtector only supports Java currently.
repo_name	'TheAlgorithms/Java'	The user/name of your repositroy
auth_token	'XXXXXX'	The access token of your account, which can be obtained here
watermark_feature	`[{'level': 'word','content': 'coprotector'},{'level': 'word','content': 'coprotector'},{'level': 'sentence','content': 'This is = A.Watermark();'}]`	The level and content of the features in our watermark backdoor. The length of the list should be `0` or `3`.
untargetd_method	`'code_corrupting'	'code_renaming'
poison_save_dir	'./test'	The path to store the poison files
poison_file_num	3	The number of poison files to be generated
poison_num	100	The number of poison instances to be genreated

This repository is protected by CoProtector. Do NOT read or run the files with confusing names.

Owner

Zhensu Sun

PhD Candidate Candidate

Zhensu Sun

GitHub Repository

This is the official PyTorch implementation of our paper: "Artistic Style Transfer with Internal-external Learning and Contrastive Learning".

Artistic Style Transfer with Internal-external Learning and Contrastive Learning This is the official PyTorch implementation of our paper: "Artistic S

51 Dec 20, 2022

A DNN inference latency prediction toolkit for accurately modeling and predicting the latency on diverse edge devices.

Note: This is an alpha (preview) version which is still under refining. nn-Meter is a novel and efficient system to accurately predict the inference l

244 Jan 06, 2023

Cweqgen - The CW Equation Generator

The CW Equation Generator The cweqgen (pronouced like "Queck-Jen") package provi

2 Jan 15, 2022

Revealing and Protecting Labels in Distributed Training

Revealing and Protecting Labels in Distributed Training

0 Nov 09, 2022

Differentiable Optimizers with Perturbations in Pytorch

Differentiable Optimizers with Perturbations in PyTorch This contains a PyTorch implementation of Differentiable Optimizers with Perturbations in Tens

54 Jun 22, 2022

An Approach to Explore Logistic Regression Models

User-centered Regression An Approach to Explore Logistic Regression Models This tool applies the potential of Attribute-RadViz in identifying correlat

0 Nov 12, 2021

WORD: Revisiting Organs Segmentation in the Whole Abdominal Region

WORD: Revisiting Organs Segmentation in the Whole Abdominal Region (Paper and DataSet). [New] Note that all the emails about the download permission o

71 Dec 22, 2022

Human Detection - Pedestrian Detection using OpenCV Python

Pedestrian Detection using OpenCV Python Follow us on Instagram for Machine Lear

1 Jan 23, 2022

Information Gain Filtration (IGF) is a method for filtering domain-specific data during language model finetuning. IGF shows significant improvements over baseline fine-tuning without data filtration.

Information Gain Filtration Information Gain Filtration (IGF) is a method for filtering domain-specific data during language model finetuning. IGF sho

4 Jul 28, 2022

Dynamic hair modeling from monocular videos using deep neural networks

Dynamic Hair Modeling The source code of the networks for our paper "Dynamic hair modeling from monocular videos using deep neural networks" (SIGGRAPH

53 Oct 18, 2022

Source code release of the paper: Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation.

GNet-pose Project Page: http://guanghan.info/projects/guided-fractal/ UPDATE 9/27/2018: Prototxts and model that achieved 93.9Pck on LSP dataset. http

83 Nov 21, 2022

O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis

O-CNN This repository contains the implementation of our papers related with O-CNN. The code is released under the MIT license. O-CNN: Octree-based Co

607 Dec 28, 2022

Repository for GNSS-based position estimation using a Deep Neural Network

Code repository accompanying our work on 'Improving GNSS Positioning using Neural Network-based Corrections'. In this paper, we present a Deep Neural

32 Dec 13, 2022

Temporal-Relational CrossTransformers

Temporal-Relational Cross-Transformers (TRX) This repo contains code for the method introduced in the paper: Temporal-Relational CrossTransformers for

83 Dec 12, 2022

Fully-automated scripts for collecting AI-related papers

AI-Paper-collector Fully-automated scripts for collecting AI-related papers List of Conferences to crawel ACL: 21-19 (including findings) EMNLP: 21-19

776 Jan 08, 2023

My coursework for Machine Learning (2021 Spring) at National Taiwan University (NTU)

Machine Learning 2021 Machine Learning (NTU EE 5184, Spring 2021) Instructor: Hung-yi Lee Course Website : (https://speech.ee.ntu.edu.tw/~hylee/ml/202

100 Dec 26, 2022

Code for "Modeling Indirect Illumination for Inverse Rendering", CVPR 2022

Modeling Indirect Illumination for Inverse Rendering Project Page | Paper | Data Preparation Set up the python environment conda create -n invrender p

116 Jan 03, 2023

Exploration & Research into cross-domain MEV. Initial focus on ETH/POLYGON.

xMEV, an apt exploration This is a small exploration on the xMEV opportunities between Polygon and Ethereum. It's a data analysis exercise on a few pa

7 Oct 18, 2022

PyTorch implementation of Advantage async actor-critic Algorithms (A3C) in PyTorch

Advantage async actor-critic Algorithms (A3C) in PyTorch @inproceedings{mnih2016asynchronous, title={Asynchronous methods for deep reinforcement lea

111 Dec 08, 2022

A certifiable defense against adversarial examples by training neural networks to be provably robust

DiffAI v3 DiffAI is a system for training neural networks to be provably robust and for proving that they are robust. The system was developed for the

202 Dec 13, 2022