تقرير
Efficient Differentially Private Secure Aggregation for Federated Learning via Hardness of Learning with Errors
| العنوان: | Efficient Differentially Private Secure Aggregation for Federated Learning via Hardness of Learning with Errors |
|---|---|
| المؤلفون: | Stevens, Timothy, Skalka, Christian, Vincent, Christelle, Ring, John, Clark, Samuel, Near, Joseph |
| سنة النشر: | 2021 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Cryptography and Security, Computer Science - Machine Learning |
| الوصف: | Federated machine learning leverages edge computing to develop models from network user data, but privacy in federated learning remains a major challenge. Techniques using differential privacy have been proposed to address this, but bring their own challenges -- many require a trusted third party or else add too much noise to produce useful models. Recent advances in \emph{secure aggregation} using multiparty computation eliminate the need for a third party, but are computationally expensive especially at scale. We present a new federated learning protocol that leverages a novel differentially private, malicious secure aggregation protocol based on techniques from Learning With Errors. Our protocol outperforms current state-of-the art techniques, and empirical results show that it scales to a large number of parties, with optimal accuracy for any differentially private federated learning scheme. Comment: 16 pages, 4 figures |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2112.06872 |
| رقم الأكسشن: | edsarx.2112.06872 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |