Philip-William Grassal

activity

20182023

most citedAssessing differentially private deep learning with Membership Inference

15 citations · 16 across the 5 of their papers we have counts for

collaborators

Showing 2021Show all

2 papers · 1 filter

cs.CV2021★ 1 cited

Neural Head Avatars from Monocular RGB Videos

Philip-William Grassal, Malte Prinzler, Titus Leistner +3

We present Neural Head Avatars, a novel neural representation that explicitly models the surface geometry and appearance of an animatable human avatar that can be used for teleconf…

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…

Neural Head Avatars from Monocular RGB Videos

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

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