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.
@article{arxiv.2501.08137,
title = {Audio-Visual Deepfake Detection With Local Temporal Inconsistencies},
author = {Marcella Astrid and Enjie Ghorbel and Djamila Aouada},
journal= {arXiv preprint arXiv:2501.08137},
year = {2025}
}