cs.CVMay 19, 2025

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

Authors: Haiquan Wen, Yiwei He, Zhenglin Huang, Tianxiao Li, Zihan Yu, Xingru Huang, Lu Qi, Baoyuan Wu, 

Organizations: University of Liverpool, UK · Hangzhou Dianzi University · Wuhan University · The Chinese University of Hong Kong, Shenzhen, Guangdong, China · 

Abstract

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 However, applying Multimodal Large Language Models (MLLMs) to video forensics is currently limited by outdated datasets, simplistic evaluation protocols, and a reliance on black-box classification.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 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 GenBuster-Bench, a diagnostic benchmark spanning three progressive tracks (In-Domain, Out-of-Domain, and In-the-Wild) to evaluate models across domain shifts and generational shifts. Finally, we develop BusterX, a simple MLLM baseline with Reinforcement Learning (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 in both detection accuracy and rationale quality.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. VidForensics-M1: Meta-Detection Reinforcement Learning with Verifiable Temporal Grounding for AI-Generated Video Forensics

    Aug 11, 2026Bowei Liu, Zheng Lu, Yuhan Bian +8Deepfake Detection

  2. REVEAL: Robust Evolution of Vision-Language Models for Explainable AI-Video Detection

    Feb 20, 2025Yun-Yun Tsai, Qingyuan Liu, Ruijian Zha +4Tool Use in VLMsVision-Language Models

  3. ManiVid: Unified and Explainable Forensic Analysis of Manipulated Videos

    Sep 25, 2026Hengrui Kang, Zhonghao Yan, Yuxuan Yang +7Video ForensicsDigital Forensics