SAVe: Self-Supervised Audio-visual Deepfake Detection Exploiting Visual Artifacts and Audio-visual Misalignment
This addresses the challenge of scalable and robust detection of audio-visual deepfakes, which is important for security and media integrity, though it appears incremental as it builds on existing self-supervised and multimodal detection approaches.
The paper tackles the problem of detecting multimodal deepfakes by proposing SAVe, a self-supervised framework that learns on authentic videos to identify visual artifacts and audio-visual misalignment, achieving competitive in-domain performance and strong cross-dataset generalization.
Multimodal deepfakes can exhibit subtle visual artifacts and cross-modal inconsistencies, which remain challenging to detect, especially when detectors are trained primarily on curated synthetic forgeries. Such synthetic dependence can introduce dataset and generator bias, limiting scalability and robustness to unseen manipulations. We propose SAVe, a self-supervised audio-visual deepfake detection framework that learns entirely on authentic videos. SAVe generates on-the-fly, identity-preserving, region-aware self-blended pseudo-manipulations to emulate tampering artifacts, enabling the model to learn complementary visual cues across multiple facial granularities. To capture cross-modal evidence, SAVe also models lip-speech synchronization via an audio-visual alignment component that detects temporal misalignment patterns characteristic of audio-visual forgeries. Experiments on FakeAVCeleb and AV-LipSync-TIMIT demonstrate competitive in-domain performance and strong cross-dataset generalization, highlighting self-supervised learning as a scalable paradigm for multimodal deepfake detection.