Federated Learning Is Not Private for Google GBoard Next Word Prediction [pdf]

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.

Computer Science Machine Learning Submitted on 30 Oct 2022 v1 https://arxiv.org/abs/2210.16947v1 , last revised 9 Oct 2023 this version, v2 Title:Two Models are Better than One: Federated Learning Is Not Private For Google GBoard Next Word Prediction View PDF https://arxiv.org/pdf/2210.16947 HTML experimental https://arxiv.org/html/2210.16947v2 Abstract: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. Submission history From: Mohamed Suliman view email https://arxiv.org/show-email/2c4a8e2d/2210.16947 Sun, 30 Oct 2022 20:58:34 UTC 1,254 KB \ v1\ https://arxiv.org/abs/2210.16947v1 v2 Mon, 9 Oct 2023 21:05:32 UTC 1,483 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 IArxiv Recommender What is IArxiv? https://iarxiv.org/about 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 .