no code implementations • 1 Oct 2024 • Kristian Schwethelm, Johannes Kaiser, Jonas Kuntzer, Mehmet Yigitsoy, Daniel Rueckert, Georgios Kaissis
This work addresses this gap by introducing differentially private active learning (DP-AL) for standard learning settings.
no code implementations • 12 Mar 2024 • Kristian Schwethelm, Johannes Kaiser, Moritz Knolle, Daniel Rueckert, Georgios Kaissis, Alexander Ziller
We propose a reconstruction attack based on diffusion models (DMs) that assumes adversary access to real-world image priors and assess its implications on privacy leakage under DP-SGD.
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.
1 code implementation • 28 Mar 2023 • Ahmad Bdeir, Kristian Schwethelm, Niels Landwehr
To address this, we present HCNN, a fully hyperbolic convolutional neural network (CNN) designed for computer vision tasks.