arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.12925cs.CRcs.AIcs.SE
收藏

CoProtector:保护Open- Source Code免受未经授权的训练使用和数据投毒

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

Monash University(蒙纳士大学);ShanghaiTech University(上海科技大学);University of Technology Sydney(悉尼科技大学)

Zhensu Sun, Xiaoning Du, Fu Song, Mingze Ni, Li Li

摘要:

Github Copilot,在数十亿行公共代码上训练,最近已经成为计算机科学研究和实践社区的流行语。虽然它旨在帮助开发人员实现具有强大智能的安全有效的代码,但实践者和研究人员对其道德和安全问题表示担忧,例如,是否应该自由地使用copyleft许可的代码,或者首先考虑使用不安全的代码进行培训?随着人工智能的快速发展,Copilot等旨在通过深度学习模型从大规模开源代码中学习知识的类似产品不可避免地会受到这些问题的严重影响。为了减轻这种影响,我们认为有必要发明有效的机制来保护开源代码不被深度学习模型利用。在这里,我们设计并实现了一个原型,CoProtector,它利用数据投毒技术来武装源代码存储库防御这种漏洞。我们的大规模实验经验表明,CoProtector可以有效地实现其目的,显著降低Copilot类深度学习模型的性能,同时能够稳定地揭示秘密嵌入的水印后门。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑