Get started
Author

Georgios Kaissis

Disparate privacy risks from medical AI
2026 · Moritz A. Knolle, Martin J. Menten, et al. · Nature · 4
Survival In-Context: Amortized Bayesian Survival Analysis via Prior-Fitted Networks
2026 · Seletkov, Dmitrii, Hager, Paul, et al. · arXiv (Cornell University) · 1
PDF
MIMIC-IV-Ext MIMIC Note Extract: A Large-Scale Structured Dataset Extracted from MIMIC-IV-Note Discharge Summaries
2026 · Kuntzer, Jonas, Schwethelm, Kristian, et al. · PhysioNet
Generalist-Specialist Mixture-of-Experts for Rare Pathology Detection in Multimodal Imaging
2026 · Kaiser, Johannes, Braunmiller, Florian, et al. · arXiv (Cornell University)
PDF
Memorisation bias in medical AI
2026 · Knolle, Moritz A., Menten, Martin J., et al. · arXiv (Cornell University)
PDF
It depends: Incorporating correlations for joint aleatoric and epistemic uncertainties of high-dimensional output spaces
2026 · Feiner, Leonhard F., Nickel, Manuel, et al. · arXiv (Cornell University)
PDF
Depth-adaptive Inference of Looped Language Models via Continuous Depth Batching
2026 · Schwethelm, Kristian, Rueckert, Daniel, et al. · arXiv (Cornell University)
PDF
Extractable Memorization From First Principles
2026 · Cooper, A. Feder, Swanberg, Marika, et al. · arXiv (Cornell University)
PDF
Beyond privacy: the potentialities of differential privacy in generative AI
2026 · Jonas Kuntzer, Johannes Kaiser, et al. · Discover Artificial Intelligence
PDF
looped-lm-scaling: Iso-Depth Scaling Laws for Looped Language Models
2026 · Schwethelm, Kristian, Rueckert, Daniel, et al. · Zenodo (CERN European Organization for Nuclear Research)
How Much Is One Recurrence Worth? Iso-Depth Scaling Laws for Looped Language Models
2026 · Schwethelm, Kristian, Rueckert, Daniel, et al. · arXiv (Cornell University)
PDF
Is your algorithm unlearning or untraining?
2026 · Triantafillou, Eleni, Humayun, Ahmed Imtiaz, et al. · arXiv (Cornell University)
PDF
Unintended Memorization of Sensitive Information in Fine-Tuned Language Models
2026 · Association for Computational Linguistics 2026, Eisenhart-Rothe, Rüdiger von, et al. · Underline Science Inc.
Redirection for Erasing Memory (REM): Towards a universal unlearning method for corrupted data
2026 · Schöpf, Stefan, Mozer, Michael, et al. · Apollo (University of Cambridge)
Optimal conversion from Rényi Differential Privacy to $f$-Differential Privacy
2026 · Riess, Anneliese, Gomez, Juan Felipe, et al. · arXiv (Cornell University)
PDF
Unintended Memorization of Sensitive Information in Fine-Tuned Language Models
2026 · Szep, Marton, Ruiz, Jorge Marin, et al. · arXiv (Cornell University)
PDF
Memorisation Bias: AI Predictions for Data Contributors Are Biased Towards Their Health States in the Training Data
2026 · Moritz Knolle, Martin J. Menten, et al. · Lecture notes in computer science
Optimal privacy guarantees for a relaxed threat model: Addressing sub-optimal adversaries in differentially private machine learning
2023 · Georgios Kaissis, Alexander Ziller, et al. · neural information processing systems
Works count: 19
Citation count: 5
H-index: 1
I10-index:
Year
Topic
Type