Konferenzbeitrag
DeDiM: De-identification using a diffusion model
Vorschaubild nicht verfügbar
Volltext URI
Dokumententyp
Text/Conference Paper
Zusatzinformation
Datum
2022
Zeitschriftentitel
ISSN der Zeitschrift
Bandtitel
Quelle
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.