Privacy Preserving AI; more

Berlin Machine Learning Group
Berlin Machine Learning Group
Öffentliche Gruppe
RSVPs öffnen am
Montag, 6. April 2020

Benötigt einen Veranstaltungsort


Talk 1: Introduction to Federated and Privacy Preserving Analytics & AI – Overview of Techniques and Tools

Speaker: Robin Roehm (apheris)

Abstract: The success of machine learning and deep learning techniques is directly proportional to the amount of data available for training the algorithms – yet data is often distributed across different datasets and data can’t be centralized due to regulatory restrictions or fear of loosing IP. New techniques out of the field of privacy preserving computations promise to solve these problems and help to break down data silos and closed data ecosystem. This session shall give an introduction to the topic of federated and privacy preserving analytics & AI. We will take a look at the intersection of cryptography and machine learning and cover the basics of technologies such as Differential Privacy, Secure Multiparty Computation, Homomorphic Encryption, Privacy Preserving Record Linkage and Federated Machine Learning. Furthermore, we will have a closer look at what use cases can be enabled by adopting these technologies.

Bio: Robin is founder and CEO of apheris AI GmbH, a start-up that develops artificial intelligence algorithms for biomedical data with a focus on privacy preserving technologies. Robin studied medicine, philosophy and mathematics and was professionally trained at UBS in Global Banking. In recent years, Robin has already founded another start-up in the healthtech sector, where he build an automatic speech recognition for children with language disorders. Prior to and during his various studies he intensively focused on data harmonization techniques using artificial intelligence and algebraic theories on privacy preserving data processing. With apheris AI he pursues the mission to fully leverage the value of biomedical data for the benefit of patients, while preserving the privacy of the data.


Talk 2: TBD