Logo des Repositoriums
 
Konferenzbeitrag

DeDiM: De-identification using a diffusion model

Lade...
Vorschaubild

Volltext URI

Dokumententyp

Text/Conference Paper

Zusatzinformation

Datum

2022

Zeitschriftentitel

ISSN der Zeitschrift

Bandtitel

Verlag

Gesellschaft für Informatik e.V.

Zusammenfassung

As a countermeasure against malicious authentication in a face recognition system using a face image obtained from SNS or the like, de-identification methods based on adversarial example have been studied. However, since adversarial example directly uses the gradient information of a face recognition model, it is highly dependent on the model, and a de-identification effect and image quality are difficult to achieve for an unknown recognition model. In this study, we propose a novel de-identification method based on a diffusion model, which has high generalizability to an unknown recognition model by applying minute changes to face shapes. Experiments using LFW showed that the proposed method has a higher de-identification effect for unknown models and better image quality than a conventional method using adversarial example.

Beschreibung

Hidetsugu Uchida, Narishige Abe and Shigefumi Yamada (2022): DeDiM: De-identification using a diffusion model. BIOSIG 2022. DOI: 10.1109/BIOSIG55365.2022.9896972. Bonn: Gesellschaft für Informatik e.V.. PISSN: 1617-5474. ISBN: 978-3-88579-723-4. pp. 72-79. Regular Research Papers. Darmstadt. 14.-16. September 2022

Zitierform

Tags