Content-Invariant Spatio-Temporal Neural Framework for Forgery Detection in Image Sequences

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F26%3A0199661" target="_blank" >RIV/00216305:26220/26:0199661 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/ICUMT67815.2025.11268794" target="_blank" >http://dx.doi.org/10.1109/ICUMT67815.2025.11268794</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICUMT67815.2025.11268794" target="_blank" >10.1109/ICUMT67815.2025.11268794</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Content-Invariant Spatio-Temporal Neural Framework for Forgery Detection in Image Sequences

Popis výsledku v původním jazyce

The increasing prevalence of deepfake videos underscores the need for effective and reliable detection methods. In this study, we propose a hybrid deepfake detection framework that integrates a static image forgery detector with a recurrent neural network (RNN) to exploit both spatial and temporal fea- tures. Specifically, we utilize an existing frame-level detector that identifies common forgery artifacts within individual frames. This is followed by a Long Short-Term Memory (LSTM) network that models temporal dependencies across frames, enabling detection of inconsistencies that are overlooked in frame-by-frame anal- ysis. Experimental results demonstrate that temporal modeling significantly improves accuracy over frame-level baselines. Our contributions are twofold: (i) we provide empirical evidence that deepfake videos exhibit detectable temporal signatures, and (ii) we construct a compact, real-world evaluation set of deepfake videos. Notably, detection performance on this dataset is lower than on standard benchmarks, suggesting a domain gap between commonly used training data and real-world deepfakes.

Název v anglickém jazyce

Content-Invariant Spatio-Temporal Neural Framework for Forgery Detection in Image Sequences

Popis výsledku anglicky

The increasing prevalence of deepfake videos underscores the need for effective and reliable detection methods. In this study, we propose a hybrid deepfake detection framework that integrates a static image forgery detector with a recurrent neural network (RNN) to exploit both spatial and temporal fea- tures. Specifically, we utilize an existing frame-level detector that identifies common forgery artifacts within individual frames. This is followed by a Long Short-Term Memory (LSTM) network that models temporal dependencies across frames, enabling detection of inconsistencies that are overlooked in frame-by-frame anal- ysis. Experimental results demonstrate that temporal modeling significantly improves accuracy over frame-level baselines. Our contributions are twofold: (i) we provide empirical evidence that deepfake videos exhibit detectable temporal signatures, and (ii) we construct a compact, real-world evaluation set of deepfake videos. Notably, detection performance on this dataset is lower than on standard benchmarks, suggesting a domain gap between commonly used training data and real-world deepfakes.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20202 - Communication engineering and systems

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

International Conference on Ultra Modern Telecommunications and Workshops

ISBN

979-8-3315-7675-2

ISSN

—

e-ISSN

2157-023X

Počet stran výsledku

5

Strana od-do

240-245

Název nakladatele

—

Místo vydání

—

Místo konání akce

Florencie, Itálie

Datum konání akce

3. 11. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—