Anneliese Riess — accepted AI-conference papers

2026

Optimal conversion from Rényi Differential Privacy to $f$-Differential Privacy

Anneliese Riess, Felipe Gomez, Flavio Calmon, Julia Schnabel, Georgios Kaissis

ICML 2026poster

We prove the conjecture stated in Appendix F.3 of Zhu et al.: among all conversion rules that map a Rényi Differential Privacy (RDP) profile $\tau \mapsto \rho(\tau)$ to a valid hypothesis-testing trade-off $f$ (or equivalently, an $(\varepsilon,\delta)$-Differential Privacy curve), the rule based o…

Cited by 1 Source ↗Scholar ↗

2023

Optimal privacy guarantees for a relaxed threat model: Addressing sub-optimal adversaries in differentially private machine learning

Georgios Kaissis, Alexander Ziller, Stefan Kolek, Anneliese Riess, Daniel Rueckert

NeurIPS 2023poster

Differentially private mechanisms restrict the membership inference capabilities of powerful (optimal) adversaries against machine learning models. Such adversaries are rarely encountered in practice. In this work, we examine a more realistic threat model relaxation, where (sub-optimal) adversaries…

Cited by 6 Source ↗PDF ↗Scholar ↗