LEVERAGING LARGE MULTIMODAL MODELS FOR AUDIO-VIDEO DEEPFAKE DETECTION: A PILOT STUDY
Songjun Cao, Yuqi Li, Yunpeng Luo, Jianjun Yin, Long Ma
Abstract
Audio-visual deepfake detection (AVD) is increasingly important as modern generators can fabricate convincing speech and video. Most current multimodal detectors are small, task-specific models: they work well on curated tests but scale poorly and generalize weakly across domains. We introduce AV-LMMDetect, a supervised fine-tuned (SFT) large multimodal model that casts AVD as a prompted yes/no classification - "Is this video real or fake?". Built on Qwen 2.5 Omni, it jointly analyzes audio and visual streams for deepfake detection and is trained in two stages: lightweight LoRA alignment followed by audio-visual encoder full fine-tuning. On FakeAVCeleb and Mavos-DD, AV-LMMDetect matches or surpasses prior methods and sets a new state of the art on Mavos-DD datasets.
BibTeX
@inproceedings{icassp2026_leveraginglargem,
title = {LEVERAGING LARGE MULTIMODAL MODELS FOR AUDIO-VIDEO DEEPFAKE DETECTION: A PILOT STUDY},
author = {Songjun Cao and Yuqi Li and Yunpeng Luo and Jianjun Yin and Long Ma},
booktitle = {ICASSP 2026},
year = {2026}
}