Jean-Philippe Bossuat

Title: Innovations by Jean-Philippe Bossuat

Introduction

Jean-Philippe Bossuat is a notable 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

One of his latest patents is titled "System and method for privacy-preserving distributed training of neural network models on distributed datasets." This invention describes a computer-implemented method and a distributed computer system that allows for the secure training of a global neural network model using data from multiple providers. Each data provider is equipped with a local training dataset and a vector of output labels. The system 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 throughout the training process.

Another significant patent by Bossuat is "System and method for privacy-preserving distributed training of machine learning models on distributed datasets." This system involves multiple data providers that are communicatively coupled, each possessing a local model and a local training dataset. The invention allows for the iterative training of local models while maintaining the privacy of the data through encryption. The data providers can combine their local models into a current global model, which is then updated and shared among the providers.

Career Highlights

Jean-Philippe Bossuat is affiliated with the École Polytechnique Fédérale de Lausanne, a prestigious institution known for its cutting-edge research and innovation in technology and engineering. His work at this institution has positioned him as a leader in the field of machine learning and data privacy.

Collaborations

Throughout his career, Bossuat has collaborated with notable colleagues such as David Froelicher and Juan Ramon Troncoso-Pastoriza. These collaborations have further enriched his research and contributed to the advancement of privacy-preserving technologies in machine learning.

Conclusion

Jean-Philippe Bossuat's innovative patents and contributions to the field of machine learning demonstrate his commitment to enhancing data privacy and security. His work continues to influence the development of advanced technologies in this critical area.