BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wen, Haiquan, He, Yiwei, Huang, Zhenglin, Li, Tianxiao, Yu, Zihan, Huang, Xingru, Qi, Lu, Wu, Baoyuan, Li, Xiangtai, Cheng, Guangliang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912946643271680
author Wen, Haiquan
He, Yiwei
Huang, Zhenglin
Li, Tianxiao
Yu, Zihan
Huang, Xingru
Qi, Lu
Wu, Baoyuan
Li, Xiangtai
Cheng, Guangliang
author_facet Wen, Haiquan
He, Yiwei
Huang, Zhenglin
Li, Tianxiao
Yu, Zihan
Huang, Xingru
Qi, Lu
Wu, Baoyuan
Li, Xiangtai
Cheng, Guangliang
contents As generative video models become increasingly realistic, detecting AI-generated videos requires systems that offer both accuracy and interpretability. However, applying Multimodal Large Language Models (MLLMs) to video forensics is currently limited by outdated datasets, simplistic evaluation protocols, and a reliance on black-box classification. To address these issues, we introduce a comprehensive dataset, benchmark, and baseline model for video forgery detection. First, we present \textbf{GenBuster-200K}, a fair dataset of over 200,000 high-quality videos sourced from state-of-the-art generators, featuring diverse real-world scenarios. Second, we propose \textbf{GenBuster-Bench}, a diagnostic benchmark spanning three progressive tracks (In-Domain, Out-of-Domain, and In-the-Wild) to evaluate models across \textit{domain shifts} and \textit{generational shifts}. It also introduces an MLLM-as-a-Judge protocol to assess the quality of the generated forensic explanations. Finally, we develop \textbf{BusterX}, an MLLM baseline with RL training. Instead of direct binary classification, BusterX formulates detection as a visual reasoning task, where the generated reasoning chain serves as detector itself. Experimental results demonstrate that BusterX outperforms several leading MLLMs (e.g., Qwen3.5, Claude-Sonnet-4.6) in both detection accuracy and rationale quality.
format Preprint
id arxiv_https___arxiv_org_abs_2505_12620
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanation
Wen, Haiquan
He, Yiwei
Huang, Zhenglin
Li, Tianxiao
Yu, Zihan
Huang, Xingru
Qi, Lu
Wu, Baoyuan
Li, Xiangtai
Cheng, Guangliang
Computer Vision and Pattern Recognition
As generative video models become increasingly realistic, detecting AI-generated videos requires systems that offer both accuracy and interpretability. However, applying Multimodal Large Language Models (MLLMs) to video forensics is currently limited by outdated datasets, simplistic evaluation protocols, and a reliance on black-box classification. To address these issues, we introduce a comprehensive dataset, benchmark, and baseline model for video forgery detection. First, we present \textbf{GenBuster-200K}, a fair dataset of over 200,000 high-quality videos sourced from state-of-the-art generators, featuring diverse real-world scenarios. Second, we propose \textbf{GenBuster-Bench}, a diagnostic benchmark spanning three progressive tracks (In-Domain, Out-of-Domain, and In-the-Wild) to evaluate models across \textit{domain shifts} and \textit{generational shifts}. It also introduces an MLLM-as-a-Judge protocol to assess the quality of the generated forensic explanations. Finally, we develop \textbf{BusterX}, an MLLM baseline with RL training. Instead of direct binary classification, BusterX formulates detection as a visual reasoning task, where the generated reasoning chain serves as detector itself. Experimental results demonstrate that BusterX outperforms several leading MLLMs (e.g., Qwen3.5, Claude-Sonnet-4.6) in both detection accuracy and rationale quality.
title BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.12620