跳到主要导航 跳到搜索 跳到主要内容

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

  • Zhensu Sun
  • , Xiaoning Du
  • , Fu Song
  • , Mingze Ni
  • , Li Li*
  • *此作品的通讯作者
  • Monash University
  • ShanghaiTech University
  • University of Technology Sydney

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

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.

源语言英语
主期刊名WWW 2022 - Proceedings of the ACM Web Conference 2022
出版商Association for Computing Machinery, Inc
652-660
页数9
ISBN(电子版)9781450390965
DOI
出版状态已出版 - 25 4月 2022
已对外发布
活动31st ACM Web Conference, WWW 2022 - Virtual, Lyon, 法国
期限: 25 4月 202229 4月 2022

出版系列

姓名WWW 2022 - Proceedings of the ACM Web Conference 2022

会议

会议31st ACM Web Conference, WWW 2022
国家/地区法国
Virtual, Lyon
时期25/04/2229/04/22

学术指纹

探究 'CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data Poisoning' 的科研主题。它们共同构成独一无二的学术指纹。

引用此