Federated Learning: Promises, Opportunities and Security Challenges

Keynote at KI 2022 conference

2022/09/21 13:30-14:50

Organizers: Gesellschaft für Informatik (GI e.V.)


Abstract

KI2022 is the 45th German Conference on Artificial Intelligence and organized in cooperation with the Fachbereich Künstliche Intelligenz der Gesellschaft für Informatik (GI-SIG AI). KI is one of the major European AI conferences and traditionally brings together academic and industrial researchers from all areas of AI, providing an ideal place for exchanging news and research results on theory and applications. At KI2022, CROSSING-PI Prof. Ahmad-Reza Sadeghi will give a key note on the topic “Federated Learning: Promises, Opportunities and Security Challenges” on September 21, 2022.

Federated Learning (FL) is a collaborative machine learning approach allowing the involved participants to jointly train a model without having to mutually share their private, potentially sensitive local datasets. As an enabling technology FL can benefit a variety of sensitive distributed applications in practice. However, despite its benefits, FL is shown to be susceptible to so-called backdoor attacks, in which an adversary injects manipulated model updates into the federated model aggregation process so that the resulting model provides targeted predictions for specific adversary-chosen inputs.

In the talk, Prof. Sadeghi will present his and his teams research and experiences, also with industrial partners, in utilizing FL to enhance the security of large scale systems and applications, as well as in building FL systems that are resilient to backdoor attacks.


Further Information

Conference Website