SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2110.12925 · 2021

CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data Poisoning

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Github Copilot, trained on billions of lines of public code, has recently become the buzzword in the computer science research and practice community. Although it is designed to help developers implement safe and effective code with powerful intelligence, practitioners and researchers raise concerns about its ethical and security problems, e.g., should the copyleft licensed code be freely leveraged or insecure code be considered for training in the first place? These problems pose a significant impact on Copilot and other similar products that aim to learn knowledge from large-scale open-source code through deep learning models, which are inevitably on the rise with the fast development of artificial intelligence. To mitigate such impacts, we argue that there is a need to invent effective mechanisms for protecting open-source code from being exploited by deep learning models. Here, we design and implement a prototype, CoProtector, which utilizes data poisoning techniques to arm source code repositories for defending against such exploits. Our large-scale experiments empirically show that CoProtector is effective in achieving its purpose, significantly reducing the performance of Copilot-like deep learning models while being able to stably reveal the secretly embedded watermark backdoors.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2110.12925")
get_code_for_paper("2110.12925")
have("2110.12925")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2110.12925.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2110.12925.svg)](https://syntology.ai/paper/2110.12925)

Connect an agent — have() is free.