CoChat
Sign Up
Cited by 34Digital Media Forensic DetectionFace recognition and analysisGenerative Adversarial Networks and Image Synthesis

Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector

Guo, Xiao, Song, Xiufeng, Zhang, Yue, Liu, Xiaohong, Liu, Xiaoming·2025·2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
DOI 10.1109/cvpr52734.2025.00019
Open this paper in CoChat — free account

Abstract

Deepfake detection is a long-established research topic vital for mitigating the spread of malicious misinformation. Unlike prior methods that provide either binary classification results or textual explanations separately, we introduce a novel method capable of generating both simultaneously. Our method harnesses the multi-modal learning capability of the pre-trained CLIP and the unprecedented interpretability of large language models (LLMs) to enhance both the generalization and explainability of deep-fake detection. Specifically, we introduce a multi-modal face forgery detector (M2F2-Det) that employs tailored face forgery prompt learning, incorporating the pre-trained CLIP to improve generalization to unseen forgeries. Also, M2F2-Det incorporates an LLM to provide detailed textual explanations of its detection decisions, enhancing interpretability by bridging the gap between natural language and subtle cues of facial forgeries. Empirically, we evaluate M2F2-Det on both detection and explanation generation tasks, where it achieves state-of-the-art performance, demonstrating its effectiveness in identifying and explaining diverse forgeries. Source code is available at $\color{magenta}{link}$.

Integrity signals

Registry

Crossref · 10.1109/cvpr52734.2025.00019

Cites

17 of 17 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Models such as TruthLens and M2F2-Det perform detection through the process of explanation itself.

    “models such as TruthLens and M2F2-Det perform detection through the process of explanation itself [40,41].”

    From From Black Boxes to Glass Boxes: Explainable AI for Trustworthy Deepfake Forensics (2025) · cites this paper as [41]

  • M2F2-Det jointly generates detection scores and textual explanations, leveraging a pre-trained CLIP model and an LLM to link subtle forgery-related visual cues with natural language descriptions.

    “Guo et al. [41] introduced M2F2-Det, a multimodal detector that jointly generates detection scores and textual explanations. The model leverages the visual representation capabilities of a pre-trained CLIP model together with the generative ability of a Large Language Model (LLM), thereby linking subtle forgeryrelated visual cues with natural language descriptions.”

    From From Black Boxes to Glass Boxes: Explainable AI for Trustworthy Deepfake Forensics (2025) · cites this paper as [41]

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Authors
Guo, X., Song, X., Zhang, Y., Liu, X., & Liu, X.
Affiliations
  • Michigan State University (US)
  • Shanghai Jiao Tong University (CN)
ORCID
Venue
2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2025-06-10
Pages
105-116
ISSN
1063-6919 (ISSN-L)
DOI
10.1109/cvpr52734.2025.00019
OpenAlex
W4413144877
Cited by
34
References
17
Citations by year
2026: 25 · 2025: 9
FWCI
25.69
Type
conference paper
Language
en
Open access
closed
Licence
Locations
IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
Keywords
deepfake detection, face forgery detection, vision-language models, CLIP, large language models, explainable AI, prompt learning, multimodal learning

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review