Privacy for Free: Communication-Efficient Learning with Differential Privacy Using Sketches

Authors: Tian Li, Zaoxing Liu, Vyas Sekar, Virginia Smith
Published: 2019-11-03 | Updated: 2019-12-06

Source: https://arxiv.org/abs/1911.00972

PDF: https://arxiv.org/pdf/1911.00972

AIにより推定されたラベル

プライバシー保証 通信効率 プライバシー管理

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

Communication and privacy are two critical concerns in distributed learning. Many existing works treat these concerns separately. In this work, we argue that a natural connection exists between methods for communication reduction and privacy preservation in the context of distributed machine learning. In particular, we prove that Count Sketch, a simple method for data stream summarization, has inherent differential privacy properties. Using these derived privacy guarantees, we propose a novel sketch-based framework (DiffSketch) for distributed learning, where we compress the transmitted messages via sketches to simultaneously achieve communication efficiency and provable privacy benefits. Our evaluation demonstrates that DiffSketch can provide strong differential privacy guarantees (e.g., ε= 1) and reduce communication by 20-50x with only marginal decreases in accuracy. Compared to baselines that treat privacy and communication separately, DiffSketch improves absolute test accuracy by 5 privacy guarantees and communication compression.