Saga: Source Attribution of Generative AI Videos (identifies the model used)

Researchers have introduced SAGA (Source Attribution of Generative AI videos), the first comprehensive framework for identifying the specific generative model used to create AI-generated videos, achieving state-of-the-art attribution using only 0.5% of source-labeled data per class. The framework provides multi-granular attribution across five levels and introduces Temporal Attention Signatures (T-Sigs) for interpretability, setting a new benchmark for synthetic video provenance in forensic and regulatory applications.

Computer Science Computer Vision and Pattern Recognition Submitted on 16 Nov 2025 v1 https://arxiv.org/abs/2511.12834v1 , last revised 2 Apr 2026 this version, v2 Title:SAGA: Source Attribution of Generative AI Videos View PDF /pdf/2511.12834 HTML experimental https://arxiv.org/html/2511.12834v2 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. Submission history From: Rohit Kundu view email /show-email/d7b69197/2511.12834 Sun, 16 Nov 2025 23:39:54 UTC 11,337 KB v1 /abs/2511.12834v1 v2 Thu, 2 Apr 2026 18:07:08 UTC 11,325 KB References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender 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 https://info.arxiv.org/labs/index.html .