Benutzer: Gast  Login
Titel:

Adversarial interference and its mitigations in privacy-preserving collaborative machine learning

Dokumenttyp:
Article
Autor(en):
Usynin, Dmitrii; Ziller, Alexander; Makowski, Marcus; Braren, Rickmer; Rueckert, Daniel; Glocker, Ben; Kaissis, Georgios; Passerat-Palmbach, Jonathan
Abstract:
When the training data for machine learning are highly personal or sensitive, collaborative approaches can help a collective of stakeholders to train a model together without having to share any data. But there are still risks to the privacy of the data. This Perspective provides an overview of potential attacks on collaborative machine learning and how these threats could be addressed. Despite the rapid increase of data available to train machine-learning algorithms in many domains, several...     »
Zeitschriftentitel:
Nat. Mach. Intell.
Jahr:
2021
Band / Volume:
3
Heft / Issue:
9
Seitenangaben Beitrag:
749-758
Volltext / DOI:
doi:10.1038/s42256-021-00390-3
TUM Einrichtung:
Institut für Diagnostische und Interventionelle Radiologie; Institut für Medizinische Statistik und Epidemiologie
 BibTeX