Zum Inhalt springen

Nur-Lesen-Fassung: Das Forschungsinformationssystem (FIS) ist aus Sicherheitsgründen vorübergehend durch diese Nur-Lesen-Fassung ersetzt. Alle öffentlichen Inhalte und Volltexte sind weiterhin abrufbar; Anmeldung, Bearbeitung, Einreichung und Statistiken stehen nicht zur Verfügung. Bei Fragen: fis@uni-bamberg.de

Start › Publikationen › Privacy-preserving datasets by capturing feature distributions with Conditional VAEs

Publikation

Privacy-preserving datasets by capturing feature distributions with Conditional VAEs

Di Salvo, Francesco; Tafler, David; Doerrich, Sebastian; u. a. (2024): Privacy-preserving datasets by capturing feature distributions with Conditional VAEs, in: Proceedings : The 35th British Machine Vision Conference 2024, S. 1–14.

Details

Fakultät/Lehrstuhl
Autorin(nen)/Autor(en)
Tafler, David
Von
... ; Doerrich, Sebastian; ...
Titel des Sammelwerks
Proceedings : The 35th British Machine Vision Conference 2024
Konferenz
BMVC 2024, The 35th British Machine Vision Conference, 25th - 28th November 2024, Glasgow
Erscheinungsjahr
2024
Sprache(n)
Englisch
URL
Abstract

Large and well-annotated datasets are essential for advancing deep learning applications, however often costly or impossible to obtain by a single entity. In many areas, including the medical domain, approaches relying on data sharing have become critical to address those challenges. While effective in increasing dataset size and diversity, data sharing raises significant privacy concerns. Commonly employed anonymization methods based on the k-anonymity paradigm often fail to preserve data diversity, affecting model robustness. This work introduces a novel approach using Conditional Variational Autoencoders (CVAEs) trained on feature vectors extracted from large pre-trained vision foundation models. Foundation models effectively detect and represent complex patterns across diverse domains, allowing the CVAE to faithfully capture the embedding space of a given data distribution to generate (sample) a diverse, privacy-respecting, and potentially unbounded set of synthetic feature vectors. Our method notably outperforms traditional approaches in both medical and natural image domains, exhibiting greater dataset diversity and higher robustness against perturbations while preserving sample privacy. These results underscore the potential of generative models to significantly impact deep learning applications in data-scarce and privacy-sensitive environments.

GND-Schlagwort(e)
Generative KI
Deep Learning
Datenschutz
Medizin
Freie Schlagwort(e)
Generative models
Privacy
Foundation models
Robustness
DDC-Klassifikation
004 Computer science
RVK-Klassifikation
ST 300
Peer Reviewed
ja
Internationale Verbreitung
ja
Dokumenttyp
Konferenzveröffentlichung
URI
Datum der Freischaltung
06.08.2025

Permalink: https://fis.uni-bamberg.de/handle/uniba/109551 · Daten als JSON · Zitieren: BibTeX · RIS

Datenstand: 15.11.2026

Eingeschränkter Lesezugriff: Anmeldung, Bearbeitung und Einreichung sind vorübergehend deaktiviert.