Unsupervised Anomaly Detection for Type-Agnostic and Cross-Domain Deepfake Detection

MEJRI, Nesryne

Download

Doctoral thesis (Dissertations and theses)

Unsupervised Anomaly Detection for Type-Agnostic and Cross-Domain Deepfake Detection

MEJRI, Nesryne

2025

Permalink
https://hdl.handle.net/10993/65407

Files (1)Send to Details Statistics Bibliography Similar publications

Files

Full Text

Thesis_NesryneMejri_final.pdf

Author postprint (81.57 MB)

Creative Commons License - Attribution, Non-Commercial

Download

All documents in ORBilu are protected by a user license.

Send to

RIS BibTex APA Chicago Permalink X Linkedin

Details

Keywords :

Unsupervised Anomaly Detection; Deepfake Detection

Disciplines :

Computer science

Author, co-author :

MEJRI, Nesryne ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2

Language :

English

Title :

Unsupervised Anomaly Detection for Type-Agnostic and Cross-Domain Deepfake Detection

Defense date :

14 July 2025

Institution :

Unilu - University of Luxembourg [Faculty of Science, Technology and Medicine (FSTM)], Luxembourg, Luxembourg

Degree :

Docteur en Informatique (DIP_DOC_0006_B)

Promotor :

AOUADA, Djamila ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2

President :

BIANCULLI, Domenico ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SVV

Jury member :

RIESS, Christian; FAU - Friedrich-Alexander-Universität Erlangen-Nürnberg > Multimedia Communications and Signal Processing Lab

EBRAHIMI, Touradj; EPFL - École Polytechnique Fédérale de Lausanne > Multimedia Signal Processing Group

OURDANE, Mohamed; Post Luxembourg > Cybersecurity department

Focus Area :

Security, Reliability and Trust

FnR Project :

FNR16763798 - UNFAKE - Unsupervised Multi-type Explainable Deepfake Detection, 2021 (01/10/2021-31/08/2025) - Nesryne Mejri
FNR16353350 - FakeDeTeR - Deepfake Detection Using Spatio-temporal-spectral Representations For Effective Learning, 2021 (01/03/2022-28/02/2025) - Djamila Aouada

Funders :

FNR - Luxembourg National Research Fund
Post Luxembourg
ESA - European Space Agency

Funding number :

BRIDGES2021/IS/16353350/FaKeDeTeR; UNFAKE, ref.16763798; SKYTRUST 4000133885/21/ NL/MH/hm

Funding text :

This work is supported by the Luxembourg National Research Fund, under the BRIDGES2021/IS/16353350/FaKeDeTeR and UNFAKE, ref.16763798 projects, by Post Luxembourg and by the European Space Agency under the project SKYTRUST 4000133885/21/ NL/MH/hm.

Available on ORBilu :

since 16 July 2025

Statistics

Number of views

145 (28 by Unilu)

Number of downloads

45 (11 by Unilu)

More statistics