Sinem Sav

Title: Sinem Sav: Innovator in Privacy-Preserving Machine Learning

Introduction

Sinem Sav is a prominent inventor based in Lausanne, Switzerland. She has made significant contributions to the field of machine learning, particularly in the area of privacy-preserving technologies. With a total of 2 patents, her work focuses on developing systems that enhance data security while enabling effective model training.

Latest Patents

Sinem Sav's latest patents include innovative methods for privacy-preserving distributed training of neural network models. The first patent describes a computer-implemented method and a distributed computer system designed for privacy-preserving distributed training of a global neural network model on distributed datasets. This system involves data providers that are communicatively coupled, each possessing a local training dataset and a vector of output labels for training the global model. The method utilizes a cryptographic distributed secret key and a corresponding collective cryptographic public key, ensuring that the weights of the global model remain encrypted. Each data provider computes and aggregates encrypted local gradients for each layer of the global model, employing forward pass and backpropagation techniques.

The second patent focuses on a system for privacy-preserving distributed training of machine learning models on distributed datasets. This system comprises multiple data providers, each with a local model and a local training dataset. The data providers utilize a portion of a cryptographic distributed secret key and a collective cryptographic public key for encryption. Each data provider trains its local model and combines it with the current global model, leading to the creation of a combined model that updates the global model. This updated global model is then shared with a subset of other data providers.

Career Highlights

Sinem Sav is currently affiliated with the École Polytechnique Fédérale de Lausanne, where she continues to advance her research in machine learning and data privacy. Her innovative work has positioned her as a leading figure in her field, contributing to the development of secure and efficient machine learning systems.

Collaborations

Sinem collaborates with notable colleagues, including Apostolos Pyrgelis and Joao Gomes De Sa E Sousa. These partnerships enhance her research efforts and contribute to the advancement of privacy-preserving technologies in machine learning.

Conclusion

Sinem Sav's contributions to privacy-preserving machine learning are noteworthy and impactful. Her innovative patents reflect her commitment to enhancing data security in the field of artificial intelligence. Through her work at the