Saved in:
Bibliographic Details
Main Authors: Zhang, Xin, Chu, Jiaming, Zhao, Jian, Jiang, Yuchu, Yang, Xu, Jin, Lei, Zhang, Chi, Li, Xuelong
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