Saved in:
Bibliographic Details
Main Authors: Wen, Qing, Li, Haohao, Ba, Zhongjie, Cheng, Peng, He, Miao, Lu, Li, Ren, Kui
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.05670
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911424369917952
author Wen, Qing
Li, Haohao
Ba, Zhongjie
Cheng, Peng
He, Miao
Lu, Li
Ren, Kui
author_facet Wen, Qing
Li, Haohao
Ba, Zhongjie
Cheng, Peng
He, Miao
Lu, Li
Ren, Kui
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_05670
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle HyperPotter: Spell the Charm of High-Order Interactions in Audio Deepfake Detection
Wen, Qing
Li, Haohao
Ba, Zhongjie
Cheng, Peng
He, Miao
Lu, Li
Ren, Kui
Sound
Artificial Intelligence
Audio and Speech Processing
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.
title HyperPotter: Spell the Charm of High-Order Interactions in Audio Deepfake Detection
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2602.05670