HyperPotter: Spell the Charm of High-Order Interactions in Audio Deepfake Detection
This work addresses the challenge of detecting realistic audio deepfakes for security applications, representing an incremental improvement by focusing on high-order interactions.
The paper tackles the problem of audio deepfake detection by modeling high-order interactions, achieving an average relative gain of 22.15% over baselines and outperforming state-of-the-art methods by 13.96% on cross-domain datasets.
Advances in AIGC technologies have enabled the synthesis of highly realistic audio deepfakes capable of deceiving human auditory perception. Although numerous audio deepfake detection (ADD) methods have been developed, most rely on local temporal/spectral features or pairwise relations, overlooking high-order interactions (HOIs). HOIs capture discriminative patterns that emerge from multiple feature components beyond their individual contributions. We propose HyperPotter, a hypergraph-based framework that explicitly models these synergistic HOIs through clustering-based hyperedges with class-aware prototype initialization. Extensive experiments demonstrate that HyperPotter surpasses its baseline by an average relative gain of 22.15% across 11 datasets and outperforms state-of-the-art methods by 13.96% on 4 challenging cross-domain datasets, demonstrating superior generalization to diverse attacks and speakers.