Daniel Bernau

activity

20182022

most citedAssessing differentially private deep learning with Membership Inference

15 citations · 19 across the 6 of their papers we have counts for

collaborators

Showing 2021Show all

2 papers · 1 filter

cs.CR2021

Quantifying identifiability to choose and audit $ε$ in differentially private deep learning

Daniel Bernau, Günther Eibl, Philip W. Grassal +2

Differential privacy allows bounding the influence that training data records have on a machine learning model. To use differential privacy in machine learning, data scientists mus…

cs.CR2021★ 1 cited

On the privacy-utility trade-off in differentially private hierarchical text classification

Dominik Wunderlich, Daniel Bernau, Francesco Aldà +2

Hierarchical text classification consists in classifying text documents into a hierarchy of classes and sub-classes. Although artificial neural networks have proved useful to perfo…

Quantifying identifiability to choose and audit ε in differentially private deep learning

On the privacy-utility trade-off in differentially private hierarchical text classification

Quantifying identifiability to choose and audit $ε$ in differentially private deep learning