H
Helen Möllering
Researcher at Technische Universität Darmstadt
Publications - 14
Citations - 203
Helen Möllering is an academic researcher from Technische Universität Darmstadt. The author has contributed to research in topics: Backdoor & Cluster analysis. The author has an hindex of 3, co-authored 13 publications receiving 28 citations.
Papers
More filters
Proceedings ArticleDOI
SAFELearn: Secure Aggregation for private FEderated Learning
Hossein Fereidooni,Samuel Marchal,Markus Miettinen,Azalia Mirhoseini,Helen Möllering,Thien Duc Nguyen,Phillip Rieger,Ahmad-Reza Sadeghi,Thomas Schneider,Hossein Yalame,Shaza Zeitouni +10 more
TL;DR: In this article, the authors present SAFELearn, a generic design for efficient private federated learning systems that protects against inference attacks that have to analyze individual clients' model updates using secure aggregation.
Posted Content
BaFFLe: Backdoor detection via Feedback-based Federated Learning.
TL;DR: This paper proposes a novel defense, dubbed BaFFLe---Backdoor detection via Feedback-based Federated Learning---to secure FL against backdoor attacks and shows that this powerful construct can achieve very high detection rates against state-of-the-art backdoor attacks, even when relying on straightforward methods to validate the model.
Proceedings ArticleDOI
BaFFLe: Backdoor Detection via Feedback-based Federated Learning
TL;DR: Backdoor detection via feedback-based federated learning (BAFFLE) as mentioned in this paper leverages data of multiple clients not only for training, but also for uncovering model poisoning.
Proceedings ArticleDOI
Balancing Quality and Efficiency in Private Clustering with Affinity Propagation
Posted Content
PEM: Privacy-preserving Epidemiological Modeling.
TL;DR: This work proposes a practical framework for privacypreserving epidemiological modeling (PEM) on contact information stored on mobile phones, like the ones collected by already deployed contact tracing apps, but unlike those apps, PEM allows for meaningful epidemiological simulations.