cs.CVOct 18, 2025

EDVD-LLaMA: Explainable Deepfake Video Detection via Multimodal Large Language Model Reasoning

Authors: Haoran Sun, Chen Cai, Huiping Zhuang, Kong Aik Lee, Lap-Pui Chau, Yi Wang

Organizations: Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong SAR · School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore · Shien-Ming Wu School of Intelligent Engineering, South China University of Technology, Guangzhou 511442, China

Abstract

The rapid development of deepfake video technology has not only facilitated artistic creation but also made it easier to spread misinformation, which is increasingly difficult to identify. Traditional deepfake video detection (DVD) methods face issues such as a lack of transparency in their principles and insufficient generalization capabilities to cope with evolving forgery techniques. This highlights an urgent need for detectors that can identify forged content and provide verifiable reasoning explanations. This paper proposes the explainable deepfake video detection (EDVD) task and designs the EDVD-LLaMA multimodal, a large language model (MLLM) reasoning framework, which provides traceable reasoning processes alongside accurate detection results and trustworthy explanations. Our approach first incorporates a Spatio-Temporal Subtle Information Tokenization (ST-SIT) to extract and fuse global and local cross-frame deepfake features, providing rich spatio-temporal semantic information input for MLLM reasoning. Second, we construct a Fine-grained Multimodal Chain-of-Thought (Fg-MCoT) mechanism, which introduces facial feature data as hard constraints during the reasoning process to achieve pixel-level spatio-temporal video localization, suppress hallucinated outputs, and enhance the reliability of the chain of thought. In addition, we build an Explainable Reasoning FF++ benchmark dataset (ER-FF++set), leveraging structured data to annotate videos and ensure quality control, thereby supporting dual supervision for reasoning and detection. Extensive experiments demonstrate that EDVD-LLaMA achieves outstanding performance and robustness in terms of detection accuracy, explainability, and its ability to handle cross-forgery methods and cross-dataset scenarios. Compared to previous DVD methods, it provides a more explainable and superior solution.

Figures & tables

Explore similar work

CardsList
  1. Beyond Static Artifacts: A Forensic Benchmark for Video Deepfake Reasoning in Vision Language Models

    Feb 25, 2026Zheyuan Gu, Qingsong Zhao, Yusong Wang +6Deepfake DetectionVideo-Language Model Evaluation

  2. Unleashing Vision-Language Semantics for Deepfake Video Detection

    Mar 25, 2026Jiawen Zhu, Yunqi Miao, Xueyi Zhang +2Deepfake DetectionVision-Language Alignment

  3. VIGIL: Part-Grounded Structured Reasoning for Generalizable Deepfake Detection

    Mar 23, 2026Xinghan Li, Junhao Xu, Jingjing ChenExplainable Deepfake DetectionDeepfake Detection