Company Filing History:
Years Active: 2022-2023
Title: Helen Moellering: Innovator in Machine Learning
Introduction
Helen Moellering is a prominent inventor based in Neuenkirchen, Germany. She has made significant contributions to the field of machine learning, particularly in enhancing the security and privacy of federated learning systems. With a total of 2 patents, her work is paving the way for more robust and privacy-preserving technologies.
Latest Patents
Helen's latest patents include "Thwarting model poisoning in federated learning" and "Privacy-preserving machine learning." The first patent presents a method for detecting model-poisoning attempts in a federated learning system. This system involves a server coordinating with clients to train a machine-learning model. The method includes receiving results from a poisoning detection analysis, which may involve analyzing class-specific misclassification rates or activation clustering of the current state of the model. The second patent outlines a computer-implemented method for instantiating a machine learning model using a host processing system. This system comprises a trusted execution environment (TEE) and an untrusted processing system (UPS). The method involves preparing a compiler that encodes the architecture of the machine learning model, receiving source data from a client processing system, and producing software that includes both untrusted and trusted components to instantiate the model.
Career Highlights
Helen Moellering is currently employed at NEC Corporation, where she continues to innovate in the field of machine learning. Her work focuses on developing methods that enhance the security and efficiency of machine learning applications.
Collaborations
Helen collaborates with notable colleagues, including Ghassan Karame and Giorgia Azzurra Marson. Their combined expertise contributes to the advancement of technologies in their field.
Conclusion
Helen Moellering is a trailblazer in the realm of machine learning, with her patents addressing critical issues in security and privacy. Her contributions are essential for the future of federated learning systems and machine learning technologies.