Skip to content
AI News HubLIVE
Original source3 min read

Can a World Model Predict a Deepfake Video? A Consistency Margin Prior for Deepfake Detection

Summary

This paper leverages the predictive video model V-JEPA 2.1 to compute prediction residuals as a consistency-margin prior for cross-dataset deepfake detection. With only 8.25M trainable parameters, the model achieves 90.5 AUC on Celeb-DFv2 when trained solely on FF++.

SourcearXiv Computer VisionAuthor: Pradip Gupta, Shubham Mandloi, Ravi Kumar Satzoda, Sujeeth Bharadwaj, Yassine Benajiba, Dan Roth
Can a World Model Predict a Deepfake Video? A Consistency Margin Prior for Deepfake Detection
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 16 Nov 2026]

Title:Can a World Model Predict a Deepfake Video? A Consistency Margin Prior for Deepfake Detection

View a PDF of the paper titled Can a World Model Predict a Deepfake Video? A Consistency Margin Prior for Deepfake Detection, by Pradip Gupta and 5 other authors

View PDF HTML (experimental)

Abstract:Deepfake detectors often perform well on the dataset they are trained on, but their performance drops when tested on videos from different datasets. In this paper, we study whether a predictive video model can provide a signal that generalizes better across datasets. Instead of relying only on generator-specific artifacts, as many existing detectors do, we use a model trained to predict natural video and measure the difference between what it predicts and what it observes in a video. Using V-JEPA 2.1, we keep the encoder frozen and adapt the predictor using rank-16 LoRA. We define the difference between the predictor output and the frozen encoder target as the prediction residual. We hypothesize that manipulated clips produce, on average, larger prediction residuals than authentic clips, and use this as our consistency-margin prior. We process these residuals using a lightweight Latent Consistency Head (LCH), which separates residual magnitude from direction for training and classification. To test whether the direction of the consistency margin affects cross-dataset generalization, we compare standard and reversed margin objectives while keeping the remaining training setup fixed. We match the two settings on FF++ validation performance before evaluating them on unseen data. The reversed-margin setting exhibits a larger cross dataset generalization gap on average, providing evidence that the direction of the consistency margin affects cross-dataset transfer. Our complete model adds only 8.25M trainable parameters, which is 2.47% of the total 334M parameters. Trained only on FF++, it achieves an AUC of 90.5 on Celeb-DFv2 and performs well across several other cross-dataset benchmarks. Our ablations show that separating residual magnitude from direction, reducing dataset-specific variation, and using a low-rank projection improve cross-dataset generalization in our experiments.

Comments: 20 pages, 4 figures, 5 tables

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2611.21846 [cs.CV]

(or arXiv:2611.21846v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2611.21846

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Pradip Gupta [view email] [v1] Mon, 16 Nov 2026 20:04:17 UTC (696 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Can a World Model Predict a Deepfake Video? A Consistency Margin Prior for Deepfake Detection, by Pradip Gupta and 5 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.CV

new | recent | 2026-11

Change to browse by:

cs

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

ResearchersAdvanced

Key points

  • Uses frozen V-JEPA 2.1 encoder and rank-16 LoRA-adapted predictor to compute prediction residuals
  • Introduces a lightweight Latent Consistency Head to separate residual magnitude from direction
  • Reversed margin objective leads to larger cross-dataset generalization gap, showing margin direction matters
  • Model adds only 2.47% parameters and performs well across multiple cross-dataset benchmarks

Highlights and analysis are generated automatically and may contain errors. Check the original source.