Work

Audio-Visual Deepfake Detection With Local Temporal Inconsistencies

Year: 2025

Type: conference-paper

Abstract: This paper proposes an audio-visual deepfake detection approach that aims to capture fine-grained temporal inconsistencies between audio and visual modalities. To achieve this, both architectural and data synthesis strategies are introduced. From an architectural perspective, a temporal distance map, coupled with an attention mechanism, is designed to capture these inconsistencies while minimizing the impact of irrelevant temporal subsequences. Moreover, we explore novel pseudo-fake generation techniques to synthesize local inconsistencies. Our approach is evaluated against state-of-the-art methods using the DFDC and FakeAVCeleb datasets, demonstrating its effectiveness in detecting audio-visual deepfakes.

Source: IEEE International Conference on Acoustics Speech and Signal Processing

DOI: 10.1109/icassp49660.2025.10889087

Authors: Marcella Astrid, Enjie Ghorbel, Djamila Aouada

Institutions: University of Luxembourg, Interdisciplinary Centre for Security, Reliability and Trust

Language: English

Topic: Digital Media Forensic Detection

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Fonds National de la Recherche Luxembourg

Award: G442019650