Two Models are Better Than One: Federated Learning is Not Private for Google GBoard Next Word Prediction
- 11 January 2024
- book chapter
- Published by Springer Nature
- p. 105-122
Abstract
No abstract availableKeywords
All Related Versions
This publication has 11 references indexed in Scilit:
- Mobile Handset Privacy: Measuring the Data iOS and Android Send to Apple and Google2021
- See through Gradients: Image Batch Recovery via GradInversion2021
- Contact Tracing App Privacy: What Data Is Shared By Europe’s GAEN Contact Tracing Apps2021
- TAG: Gradient Attack on Transformer-based Language Models2021
- Deep Leakage from Gradients2020
- Using the Output Embedding to Improve Language Models2017
- Deep Learning with Differential Privacy2016
- LSTM: A Search Space OdysseyIEEE Transactions on Neural Networks and Learning Systems, 2016
- Text message corpus: Applying natural language processing to mobile device forensics2013
- Computation of normalized edit distance and applicationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1993