Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Haoyu, Gong, Chaoyu, He, Mengke, Li, Jiate, Han, Kai, Luo, Siqiang
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2508.05526
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911342064041984
author Liu, Haoyu
Gong, Chaoyu
He, Mengke
Li, Jiate
Han, Kai
Luo, Siqiang
author_facet Liu, Haoyu
Gong, Chaoyu
He, Mengke
Li, Jiate
Han, Kai
Luo, Siqiang
contents The proliferation of generative video models has made detecting AI-generated and manipulated videos an urgent challenge. Existing detection approaches often fail to generalize across diverse manipulation types due to their reliance on isolated spatial, temporal, or spectral information, and typically require large models to perform well. This paper introduces SSTGNN, a lightweight Spatial-Spectral-Temporal Graph Neural Network framework that represents videos as structured graphs, enabling joint reasoning over spatial inconsistencies, temporal artifacts, and spectral distortions. SSTGNN incorporates learnable spectral filters and spatial-temporal differential modeling into a unified graph-based architecture, capturing subtle manipulation traces more effectively. Extensive experiments on diverse benchmark datasets demonstrate that SSTGNN not only achieves superior performance in both in-domain and cross-domain settings, but also offers strong efficiency and resource allocation. Remarkably, SSTGNN accomplishes these results with up to 42$\times$ fewer parameters than state-of-the-art models, making it highly lightweight and resource-friendly for real-world deployment.
format Preprint
id arxiv_https___arxiv_org_abs_2508_05526
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle When Deepfake Detection Meets Graph Neural Network:a Unified and Lightweight Learning Framework
Liu, Haoyu
Gong, Chaoyu
He, Mengke
Li, Jiate
Han, Kai
Luo, Siqiang
Computer Vision and Pattern Recognition
The proliferation of generative video models has made detecting AI-generated and manipulated videos an urgent challenge. Existing detection approaches often fail to generalize across diverse manipulation types due to their reliance on isolated spatial, temporal, or spectral information, and typically require large models to perform well. This paper introduces SSTGNN, a lightweight Spatial-Spectral-Temporal Graph Neural Network framework that represents videos as structured graphs, enabling joint reasoning over spatial inconsistencies, temporal artifacts, and spectral distortions. SSTGNN incorporates learnable spectral filters and spatial-temporal differential modeling into a unified graph-based architecture, capturing subtle manipulation traces more effectively. Extensive experiments on diverse benchmark datasets demonstrate that SSTGNN not only achieves superior performance in both in-domain and cross-domain settings, but also offers strong efficiency and resource allocation. Remarkably, SSTGNN accomplishes these results with up to 42$\times$ fewer parameters than state-of-the-art models, making it highly lightweight and resource-friendly for real-world deployment.
title When Deepfake Detection Meets Graph Neural Network:a Unified and Lightweight Learning Framework
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.05526