{"slug": "saga-source-attribution-of-generative-ai-videos-identifies-the-model-used", "title": "Saga: Source Attribution of Generative AI Videos (identifies the model used)", "summary": "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.", "body_md": "# Computer Science > Computer Vision and Pattern Recognition\n\n[Submitted on 16 Nov 2025 (\n\n[v1](https://arxiv.org/abs/2511.12834v1)), last revised 2 Apr 2026 (this version, v2)]# Title:SAGA: Source Attribution of Generative AI Videos\n\n[View PDF](/pdf/2511.12834)\n\n[HTML (experimental)](https://arxiv.org/html/2511.12834v2)\n\nAbstract: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.\n\n## Submission history\n\nFrom: Rohit Kundu [[view email](/show-email/d7b69197/2511.12834)]\n\n**Sun, 16 Nov 2025 23:39:54 UTC (11,337 KB)**\n\n[[v1]](/abs/2511.12834v1)**[v2]** Thu, 2 Apr 2026 18:07:08 UTC (11,325 KB)\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth 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.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/saga-source-attribution-of-generative-ai-videos-identifies-the-model-used", "canonical_source": "https://arxiv.org/abs/2511.12834", "published_at": "2026-07-25 11:41:38+00:00", "updated_at": "2026-07-25 11:52:11.247957+00:00", "lang": "en", "topics": ["artificial-intelligence", "computer-vision", "ai-research", "ai-safety", "ai-policy"], "entities": ["SAGA", "Temporal Attention Signatures", "Rohit Kundu"], "alternates": {"html": "https://wpnews.pro/news/saga-source-attribution-of-generative-ai-videos-identifies-the-model-used", "markdown": "https://wpnews.pro/news/saga-source-attribution-of-generative-ai-videos-identifies-the-model-used.md", "text": "https://wpnews.pro/news/saga-source-attribution-of-generative-ai-videos-identifies-the-model-used.txt", "jsonld": "https://wpnews.pro/news/saga-source-attribution-of-generative-ai-videos-identifies-the-model-used.jsonld"}}