{"slug": "federated-learning-is-not-private-for-google-gboard-next-word-prediction-pdf", "title": "Federated Learning Is Not Private for Google GBoard Next Word Prediction [pdf]", "summary": "Researchers Mohamed Suliman and colleagues published an arXiv paper on 30 October 2022, revised 9 October 2023, showing that federated learning does not protect user privacy in Google's GBoard next word prediction model. The attacks recover the words a user types on a mobile handset with high accuracy under a wide range of conditions, and reconstruct word order and full sentences with high fidelity, while countermeasures such as mini-batches and adding local noise proved ineffective. The authors flag privacy concerns because GBoard, an early production adopter of federated learning, remains in active use.", "body_md": "# Computer Science > Machine Learning\n\n  [Submitted on 30 Oct 2022 (\n\n[v1](https://arxiv.org/abs/2210.16947v1)), last revised 9 Oct 2023 (this version, v2)]\n# Title:Two Models are Better than One: Federated Learning Is Not Private For Google GBoard Next Word Prediction\n\n[View PDF](https://arxiv.org/pdf/2210.16947)\n\n[HTML (experimental)](https://arxiv.org/html/2210.16947v2)\n\nAbstract:In this paper we present new attacks against federated learning when used to train natural language text models. We illustrate the effectiveness of the attacks against the next word prediction model used in Google's GBoard app, a widely used mobile keyboard app that has been an early adopter of federated learning for production use. We demonstrate that the words a user types on their mobile handset, e.g. when sending text messages, can be recovered with high accuracy under a wide range of conditions and that counter-measures such a use of mini-batches and adding local noise are ineffective. We also show that the word order (and so the actual sentences typed) can be reconstructed with high fidelity. This raises obvious privacy concerns, particularly since GBoard is in production use.\n    \n\n## Submission history\n\nFrom: Mohamed Suliman [\n[view email](https://arxiv.org/show-email/2c4a8e2d/2210.16947)]\n\n**Sun, 30 Oct 2022 20:58:34 UTC (1,254 KB)**\n\n[\\[v1\\]](https://arxiv.org/abs/2210.16947v1)\n**[v2]** Mon, 9 Oct 2023 21:05:32 UTC (1,483 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/))\n# 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))\n# 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))\nIArxiv Recommender\n\n*(*[What is IArxiv?](https://iarxiv.org/about))\n# 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/federated-learning-is-not-private-for-google-gboard-next-word-prediction-pdf", "canonical_source": "https://arxiv.org/abs/2210.16947", "published_at": "2026-09-19 00:45:06+00:00", "updated_at": "2026-09-19 00:54:53.917782+00:00", "lang": "en", "topics": ["machine-learning", "natural-language-processing", "ai-safety", "ai-ethics", "artificial-intelligence"], "entities": ["Google", "GBoard", "arXiv", "Mohamed Suliman", "federated learning"], "alternates": {"html": "https://wpnews.pro/news/federated-learning-is-not-private-for-google-gboard-next-word-prediction-pdf", "markdown": "https://wpnews.pro/news/federated-learning-is-not-private-for-google-gboard-next-word-prediction-pdf.md", "text": "https://wpnews.pro/news/federated-learning-is-not-private-for-google-gboard-next-word-prediction-pdf.txt", "jsonld": "https://wpnews.pro/news/federated-learning-is-not-private-for-google-gboard-next-word-prediction-pdf.jsonld"}}