With the development of industrial Internet of things (IIoT), Cloud Manufacturing has been increasingly popular to the manufacturing industry. It can provide resource-sharing and on-demand manufacturing services as well as automatic collaborative manufacturing with the help of edge Programmable Logic Controllers (edge-PLCs). In such a system, there is a high risk of exposing user privacy and trading secret, due to exposure of sensitive transaction data to public servers. We propose a new privacy-preserving resource-trading scheme (PRTS), which leverages the concept of homomorphic cryptography and asymmetric searchable encryption, to simultaneously protect the privacy of the equipment factory and parts factories, while supporting best matching results in terms of parts parameters and price. Furthermore, a random forest-based method is applied to identify abnormal participants. The experimental results and security analysis show that the proposed scheme is accurate, effective, and secure, even under Off-line Keyword Guessing Attacks. Finally, encrypted data can resist analysis from mainstream machine learning techniques.

随着工业物联网（IIoT）的发展，云制造在制造业中越来越受欢迎。它可以在边缘可编程逻辑控制器（edge-PLC）的帮助下提供资源共享和按需制造服务，以及自动协作制造。在这样的系统中，由于敏感交易数据暴露于公共服务器，因此存在暴露用户隐私和商业秘密的高风险。我们提出了一种新的隐私保护资源交易方案（PRTS），该方案利用同态密码学和非对称可搜索加密的概念，同时保护设备工厂和零件工厂的隐私，同时在零件参数方面支持最佳匹配结果和价格。此外，应用基于森林的随机方法来识别异常参与者。实验结果和安全性分析表明，即使在离线关键字猜测攻击下，该方案也是准确，有效，安全的。最后，加密数据可以抵抗主流机器学习技术的分析。