David Froelicher

Title: Innovations of David Froelicher

Introduction

David Froelicher is an accomplished inventor based in Lausanne, Switzerland. He has made significant contributions to the field of privacy-preserving distributed training of neural network models. With a total of 2 patents, his work focuses on enhancing the security and efficiency of machine learning processes.

Latest Patents

Froelicher's latest patents include a "System and method for privacy-preserving distributed training of neural network models on distributed datasets." This invention outlines a computer-implemented method and a distributed computer system designed for the secure training of a global neural network model. The system connects data providers, each with a local training dataset and a vector of output labels. It employs a cryptographic distributed secret key and a collective public key from a multiparty fully homomorphic encryption scheme, ensuring that the weights of the global model remain encrypted. Each data provider computes and aggregates encrypted local gradients, updating the global model based on these combined gradients.

Another notable patent is the "System and method for privacy-preserving distributed training of machine learning models on distributed datasets." This system involves multiple data providers, each with a local model and training dataset. It utilizes a portion of a cryptographic distributed secret key and a collective public key for encryption. The data providers train their local models and combine them into a current local model, which is then used to update the global model. This innovative approach enhances the collaborative training of machine learning models while maintaining data privacy.

Career Highlights

David Froelicher is affiliated with the École Polytechnique Fédérale de Lausanne, a prestigious institution known for its cutting-edge research and innovation. His work at this institution has allowed him to explore advanced methodologies in machine learning and data security.

Collaborations

Froelicher collaborates with notable colleagues such as Juan Ramon Troncoso-Pastoriza and Apostolos Pyrgelis. Their combined expertise contributes to the development of innovative solutions in the field of machine learning.

Conclusion

David Froelicher's contributions to privacy-preserving distributed training of neural network models highlight his role as a leading inventor in the field. His patents reflect a commitment to advancing technology while ensuring data security.