PrivCode:代码生成隐私保护策略  

PrivCode:Privacy protection protocol for code generation

作　　者：杨琴 石林[1] 徐守坤[1] 张华君 YANG Qin;SHI Lin;XU Shou-kun;ZHANG Hua-jun(School of Computer Science and Artificial Intelligence,Changzhou University,Changzhou 213164,China)

机构地区：[1]常州大学计算机与人工智能学院,江苏常州213164

出　　处：《计算机工程与设计》2024年第12期3546-3552,共7页Computer Engineering and Design

基　　金：江苏省石化过程关键设备数字孪生技术工程研究中心基金项目(苏发高高新发[2019]1125号)。

摘　　要：为解决用户使用Copilot等代码生成工具时面临的数据隐私泄露的问题,提出一种在线代码生成隐私保护策略PrivCode。考虑到当前机器学习隐私保护策略往往是基于白盒的前提设计的,难以适用不可知结构下的大型模型,将Copilot视为黑盒并引入代理服务器,通过Mix-Net混淆多个用户的请求,打破用户和代码生成请求之间的映射关系。1-out-of-N不经意传输确保用户接收代码提示的安全。该策略满足定义的3条性质,实验测算结果表明,协议在实际场景中可用。该策略兼顾了用户的安全以及使用需求。To address the issue of data privacy leakage that users may encounter when using code generation tools like Copilot,a privacy protection strategy for online code generation called PrivCode was proposed.Considering that current machine learning privacy protection strategies are often designed on the premise of a white-box model,which is difficult to apply to large models with unknown structures,Copilot was treated as a black-box and a proxy server was introduced using this strategy.Requests from multiple users were mixed by using Mix-Net,thereby breaking the mapping relationship between users and code generation requests.Secure delivery of code suggestions to users was ensured through the 1-out-of-N oblivious transfer.Three defined properties are satisfied and its practicality in real-world scenarios is indicated by experimental results.This strategy keeps a balance between user security and usage requirements.

关 键 词：隐私保护 代码生成 混淆网络 数据安全 不经意传输 双线性映射 匿名 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]