HeadCraft: Modeling High-Detail Shape Variations for Animated 3DMMs

Autor: Sevastopolsky, Artem, Grassal, Philip-William, Giebenhain, Simon, Athar, ShahRukh, Verdoliva, Luisa, Niessner, Matthias

Current advances in human head modeling allow to generate plausible-looking 3D head models via neural representations. Nevertheless, constructing complete high-fidelity head models with explicitly controlled animation remains an issue. Furthermore, c

Externí odkaz: http://arxiv.org/abs/2312.14140

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

Autor: Bernau, Daniel, Eibl, Günther, Grassal, Philip W., Keller, Hannah, Kerschbaum, Florian

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 must choose privacy parameters $(\epsilon,\delta)$. Choosing meaningful p

Externí odkaz: http://arxiv.org/abs/2103.02913

The Influence of Differential Privacy on Short Term Electric Load Forecasting

Autor: Eibl, Günther, Bao, Kaibin, Grassal, Philip-William, Bernau, Daniel, Schmeck, Hartmut

There has been a large number of contributions on privacy-preserving smart metering with Differential Privacy, addressing questions from actual enforcement at the smart meter to billing at the energy provider. However, exploitation is mostly limited

Externí odkaz: http://arxiv.org/abs/1807.02361

Neural Head Avatars from Monocular RGB Videos

Autor: Grassal, Philip-William, Prinzler, Malte, Leistner, Titus, Rother, Carsten, Nießner, Matthias, Thies, Justus

Publikováno v: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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 teleconferencing in AR/VR or other applications in the movie or games industry

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6ba509be2a93d7bab10e1e0f84d1f864
https://doi.org/10.1109/cvpr52688.2022.01810

Comparing Local and Central Differential Privacy Using Membership Inference Attacks

Autor: Steffen Schneider, Florian Kerschbaum, Daniel Bernau, Philip-William Grassal, Jonas Robl

Publikováno v: Data and Applications Security and Privacy XXXV ISBN: 9783030812416
DBSec
Lecture Notes in Computer Science
Lecture Notes in Computer Science-Data and Applications Security and Privacy XXXV
35th Annual IFIP WG 11.3 Conference on Data and Applications Security and Privacy (DBSec 2021)

Attacks that aim to identify the training data of neural networks represent a severe threat to the privacy of individuals in the training dataset. A possible protection is offered by anonymization of the training data or training function with differ

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::475db1987ed599352826a35ff75e7a48
https://doi.org/10.1007/978-3-030-81242-3_2