Yupeng Zhang

Title: The Innovative Contributions of Yupeng Zhang

Introduction

Yupeng Zhang is a prominent inventor based in College Park, MD (US), known for his significant contributions to the field of privacy-preserving machine learning. With a total of five patents to his name, Zhang has made strides in developing efficient protocols that enhance data security in machine learning applications.

Latest Patents

Zhang's latest patents focus on privacy-preserving machine learning. He has developed new and efficient protocols for training machine learning models, including linear regression, logistic regression, and neural networks using the stochastic gradient descent method. These protocols utilize a two-server model, allowing data owners to distribute their private data among two non-colluding servers. This setup enables the training of various models on joint data through secure two-party computation (2PC). Additionally, Zhang's techniques support secure arithmetic operations on shared decimal numbers and propose multiparty computation-friendly alternatives to non-linear functions, such as sigmoid and softmax.

Career Highlights

Throughout his career, Zhang has worked with notable companies, including Emc IP Holding Company LLC and Visa International Service Association. His experience in these organizations has contributed to his expertise in the field of machine learning and data security.

Collaborations

Zhang has collaborated with esteemed colleagues, including Nikolaos Triandopoulos and Payman Mohassel. These partnerships have further enriched his research and development efforts in privacy-preserving technologies.

Conclusion

Yupeng Zhang's innovative work in privacy-preserving machine learning has established him as a key figure in the field. His patents and collaborations reflect his commitment to advancing data security in machine learning applications.