AI News HubLIVE
In-site rewrite2 min read

SAGA: Source Attribution of Generative AI Videos

SAGA (Source Attribution of Generative AI videos) is the first comprehensive framework for large-scale attribution of AI-generated videos to the specific generative model, going beyond binary real/fake detection. It offers multi-granular attribution across five levels: authenticity, generation task (T2V/I2V), model version, development team, and precise generator. Using a novel video transformer architecture and a data-efficient pretrain-and-attribute strategy, SAGA achieves state-of-the-art performance with only 0.5% labeled data per class, and introduces Temporal Attention Signatures (T-Sigs) for interpretability.

SourceHacker News AIAuthor: giuliomagnifico

-->

[Submitted on 16 Nov 2025 (v1), last revised 2 Apr 2026 (this version, v2)]

Title:SAGA: Source Attribution of Generative AI Videos

View a PDF of the paper titled SAGA: Source Attribution of Generative AI Videos, by Rohit Kundu and 5 other authors

View PDF HTML (experimental)

Abstract:The proliferation of generative AI has led to hyper-realistic synthetic videos, escalating misuse risks and outstripping binary real/fake detectors. We introduce SAGA (Source Attribution of Generative AI videos), the first comprehensive framework to address the urgent need for AI-generated video source attribution at a large scale. Unlike traditional detection, SAGA identifies the specific generative model used. It uniquely provides multi-granular attribution across five levels: authenticity, generation task (e.g., T2V/I2V), model version, development team, and the precise generator, offering far richer forensic insights. Our novel video transformer architecture, leveraging features from a robust vision foundation model, effectively captures spatio-temporal artifacts. Critically, we introduce a data-efficient pretrain-and-attribute strategy, enabling SAGA to achieve state-of-the-art attribution using only 0.5\% of source-labeled data per class, matching fully supervised performance. Furthermore, we propose Temporal Attention Signatures (T-Sigs), a novel interpretability method that visualizes learned temporal differences, offering the first explanation for why different video generators are distinguishable. Extensive experiments on public datasets, including cross-domain scenarios, demonstrate that SAGA sets a new benchmark for synthetic video provenance, providing crucial, interpretable insights for forensic and regulatory applications.

Subjects:

Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)

Cite as: arXiv:2511.12834 [cs.CV]

(or arXiv:2511.12834v2 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2511.12834

arXiv-issued DOI via DataCite

Submission history

From: Rohit Kundu [view email] [v1] Sun, 16 Nov 2025 23:39:54 UTC (11,337 KB)

[v2] Thu, 2 Apr 2026 18:07:08 UTC (11,325 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled SAGA: Source Attribution of Generative AI Videos, by Rohit Kundu and 5 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CV

new | recent | 2025-11

Change to browse by:

cs cs.AI

References & Citations

NASA ADS

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?)