no code implementations • 20 Feb 2024 • Alexander Ziller, Anneliese Riess, Kristian Schwethelm, Tamara T. Mueller, Daniel Rueckert, Georgios Kaissis
When training ML models with differential privacy (DP), formal upper bounds on the success of such reconstruction attacks can be provided.
no code implementations • 5 Dec 2023 • Alexander Ziller, Tamara T. Mueller, Simon Stieger, Leonhard Feiner, Johannes Brandt, Rickmer Braren, Daniel Rueckert, Georgios Kaissis
Although a lower budget decreases the risk of information leakage, it typically also reduces the performance of such models.
1 code implementation • 26 Sep 2023 • Kyriaki-Margarita Bintsi, Tamara T. Mueller, Sophie Starck, Vasileios Baltatzis, Alexander Hammers, Daniel Rueckert
We conclude that static graph construction approaches are potentially insufficient for the task of brain age estimation and make recommendations for alternative research directions.
no code implementations • 28 Aug 2023 • Sophie Starck, Vasiliki Sideri-Lampretsa, Jessica J. M. Ritter, Veronika A. Zimmer, Rickmer Braren, Tamara T. Mueller, Daniel Rueckert
We demonstrate different applications of these atlases, using the differences between subjects with medical conditions such as diabetes and cardiovascular diseases and healthy subjects from the atlas space.
no code implementations • 13 Jul 2023 • Tamara T. Mueller, Sophie Starck, Leonhard F. Feiner, Kyriaki-Margarita Bintsi, Daniel Rueckert, Georgios Kaissis
In this work, we introduce extended graph assessment metrics (GAMs) for regression tasks and continuous adjacency matrices.
no code implementations • 13 Jul 2023 • Tamara T. Mueller, Siyu Zhou, Sophie Starck, Friederike Jungmann, Alexander Ziller, Orhun Aksoy, Danylo Movchan, Rickmer Braren, Georgios Kaissis, Daniel Rueckert
Body fat volume and distribution can be a strong indication for a person's overall health and the risk for developing diseases like type 2 diabetes and cardiovascular diseases.
1 code implementation • 13 Jul 2023 • Alexander Ziller, Ayhan Can Erdur, Marwa Trigui, Alp Güvenir, Tamara T. Mueller, Philip Müller, Friederike Jungmann, Johannes Brandt, Jan Peeken, Rickmer Braren, Daniel Rueckert, Georgios Kaissis
Training Artificial Intelligence (AI) models on 3D images presents unique challenges compared to the 2D case: Firstly, the demand for computational resources is significantly higher, and secondly, the availability of large datasets for pre-training is often limited, impeding training success.
no code implementations • 13 Jul 2023 • Tamara T. Mueller, Maulik Chevli, Ameya Daigavane, Daniel Rueckert, Georgios Kaissis
Our findings highlight the potential and the challenges of this specific DP application area.
no code implementations • 18 Nov 2022 • Tamara T. Mueller, Stefan Kolek, Friederike Jungmann, Alexander Ziller, Dmitrii Usynin, Moritz Knolle, Daniel Rueckert, Georgios Kaissis
Differential privacy (DP) is typically formulated as a worst-case privacy guarantee over all individuals in a database.
no code implementations • 17 Mar 2022 • Tamara T. Mueller, Dmitrii Usynin, Johannes C. Paetzold, Daniel Rueckert, Georgios Kaissis
In this work, we study the applications of differential privacy (DP) in the context of graph-structured data.
1 code implementation • 5 Feb 2022 • Tamara T. Mueller, Johannes C. Paetzold, Chinmay Prabhakar, Dmitrii Usynin, Daniel Rueckert, Georgios Kaissis
In this work, we introduce differential privacy for graph-level classification, one of the key applications of machine learning on graphs.
1 code implementation • 22 Sep 2021 • Tamara T. Mueller, Alexander Ziller, Dmitrii Usynin, Moritz Knolle, Friederike Jungmann, Daniel Rueckert, Georgios Kaissis
However, while techniques such as individual R\'enyi DP (RDP) allow for granular, per-person privacy accounting, few works have investigated the impact of each input feature on the individual's privacy loss.