← Search

Lukas Prediger

2 accepted papers

2025

Privacy-Preserving Neural Processes for Probabilistic User Modeling

UAI 2025

Uncertainty-aware user modeling is crucial for designing AI systems that adapt to users in real-time while addressing privacy concerns. This paper proposes a novel framework for privacy-preserving probabilistic user modeling that integrates uncertainty quantification and differential privacy (DP). B

Cited by 0SourcePDFScholar
2021

Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT

AISTATS 2021poster

We propose a numerical accountant for evaluating the tight (ε,δ)-privacy loss for algorithms with discrete one dimensional output. The method is based on the privacy loss distribution formalism and it uses the recently introduced fast Fourier transform based accounting technique. We carry out an err…