Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915974433734656 |
|---|---|
| author | Li, Tianxiao Huang, Zhenglin Wen, Haiquan He, Yiwei Li, Xinze Zhu, Bingyu Duan, Wuhui Chen, Congang Fu, Zeyu Dong, Yi Wu, Baoyuan Li, Jason Cheng, Guangliang |
| author_facet | Li, Tianxiao Huang, Zhenglin Wen, Haiquan He, Yiwei Li, Xinze Zhu, Bingyu Duan, Wuhui Chen, Congang Fu, Zeyu Dong, Yi Wu, Baoyuan Li, Jason Cheng, Guangliang |
| contents | Multimodal deepfakes are proliferating on social media and threaten authenticity, information integrity, and digital forensics. Existing benchmarks are constrained by their single-modality scope, simplified manipulations, or unrealistic distributions, which limit their ability to assess real-world robustness. To address these limitations, we present Omni-Fake, a unified omni-dataset for comprehensive multimodal deepfake detection in social-media settings. It comprises Omni-Fake-Set, a large-scale, high-quality dataset with 1M+ samples, and Omni-Fake-OOD, an out-of-distribution benchmark with 200k+ samples intentionally excluded from training to evaluate generalization. Omni-Fake spans four modalities (image, audio, video, and audio-video talking head) and supports a joint detection-localization-explanation protocol. On top of Omni-Fake, we further propose Omni-Fake-R1, a reinforcement-learning-driven multimodal detector that adaptively integrates visual and auditory cues and outputs structured decisions, localization, and natural-language explanations. Extensive experiments show significant gains in detection accuracy, cross-modal generalization, and explainability over state-of-the-art baselines. Project page: https://tianxiao1201.github.io/omni-fake-project-page/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_01638 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection Li, Tianxiao Huang, Zhenglin Wen, Haiquan He, Yiwei Li, Xinze Zhu, Bingyu Duan, Wuhui Chen, Congang Fu, Zeyu Dong, Yi Wu, Baoyuan Li, Jason Cheng, Guangliang Computer Vision and Pattern Recognition Multimodal deepfakes are proliferating on social media and threaten authenticity, information integrity, and digital forensics. Existing benchmarks are constrained by their single-modality scope, simplified manipulations, or unrealistic distributions, which limit their ability to assess real-world robustness. To address these limitations, we present Omni-Fake, a unified omni-dataset for comprehensive multimodal deepfake detection in social-media settings. It comprises Omni-Fake-Set, a large-scale, high-quality dataset with 1M+ samples, and Omni-Fake-OOD, an out-of-distribution benchmark with 200k+ samples intentionally excluded from training to evaluate generalization. Omni-Fake spans four modalities (image, audio, video, and audio-video talking head) and supports a joint detection-localization-explanation protocol. On top of Omni-Fake, we further propose Omni-Fake-R1, a reinforcement-learning-driven multimodal detector that adaptively integrates visual and auditory cues and outputs structured decisions, localization, and natural-language explanations. Extensive experiments show significant gains in detection accuracy, cross-modal generalization, and explainability over state-of-the-art baselines. Project page: https://tianxiao1201.github.io/omni-fake-project-page/ |
| title | Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.01638 |