Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.17282 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917120619577344 |
|---|---|
| author | Zhang, Xin Chu, Jiaming Zhao, Jian Jiang, Yuchu Yang, Xu Jin, Lei Zhang, Chi Li, Xuelong |
| author_facet | Zhang, Xin Chu, Jiaming Zhao, Jian Jiang, Yuchu Yang, Xu Jin, Lei Zhang, Chi Li, Xuelong |
| contents | Deepfake detection is a critical task in identifying manipulated multimedia content. In real-world scenarios, deepfake content can manifest across multiple modalities, including audio and video. To address this challenge, we present ERF-BA-TFD+, a novel multimodal deepfake detection model that combines enhanced receptive field (ERF) and audio-visual fusion. Our model processes both audio and video features simultaneously, leveraging their complementary information to improve detection accuracy and robustness. The key innovation of ERF-BA-TFD+ lies in its ability to model long-range dependencies within the audio-visual input, allowing it to better capture subtle discrepancies between real and fake content. In our experiments, we evaluate ERF-BA-TFD+ on the DDL-AV dataset, which consists of both segmented and full-length video clips. Unlike previous benchmarks, which focused primarily on isolated segments, the DDL-AV dataset allows us to assess the model's performance in a more comprehensive and realistic setting. Our method achieves state-of-the-art results on this dataset, outperforming existing techniques in terms of both accuracy and processing speed. The ERF-BA-TFD+ model demonstrated its effectiveness in the "Workshop on Deepfake Detection, Localization, and Interpretability," Track 2: Audio-Visual Detection and Localization (DDL-AV), and won first place in this competition. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_17282 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ERF-BA-TFD+: A Multimodal Model for Audio-Visual Deepfake Detection Zhang, Xin Chu, Jiaming Zhao, Jian Jiang, Yuchu Yang, Xu Jin, Lei Zhang, Chi Li, Xuelong Artificial Intelligence Sound Deepfake detection is a critical task in identifying manipulated multimedia content. In real-world scenarios, deepfake content can manifest across multiple modalities, including audio and video. To address this challenge, we present ERF-BA-TFD+, a novel multimodal deepfake detection model that combines enhanced receptive field (ERF) and audio-visual fusion. Our model processes both audio and video features simultaneously, leveraging their complementary information to improve detection accuracy and robustness. The key innovation of ERF-BA-TFD+ lies in its ability to model long-range dependencies within the audio-visual input, allowing it to better capture subtle discrepancies between real and fake content. In our experiments, we evaluate ERF-BA-TFD+ on the DDL-AV dataset, which consists of both segmented and full-length video clips. Unlike previous benchmarks, which focused primarily on isolated segments, the DDL-AV dataset allows us to assess the model's performance in a more comprehensive and realistic setting. Our method achieves state-of-the-art results on this dataset, outperforming existing techniques in terms of both accuracy and processing speed. The ERF-BA-TFD+ model demonstrated its effectiveness in the "Workshop on Deepfake Detection, Localization, and Interpretability," Track 2: Audio-Visual Detection and Localization (DDL-AV), and won first place in this competition. |
| title | ERF-BA-TFD+: A Multimodal Model for Audio-Visual Deepfake Detection |
| topic | Artificial Intelligence Sound |
| url | https://arxiv.org/abs/2508.17282 |