CRJul 16, 2021

BRR: Preserving Privacy of Text Data Efficiently on Device

arXiv:2107.07923v18 citations
Originality Highly original
AI Analysis

This addresses privacy concerns for users of internet-connected devices in tasks like searches and shopping, offering a practical on-device solution without requiring a trusted third party.

The paper tackles the problem of preserving user privacy for text data on personal devices by proposing an efficient on-device mechanism that provides metric differential privacy, showing similar or better utility than state-of-the-art methods while reducing storage costs by orders of magnitude.

With the use of personal devices connected to the Internet for tasks such as searches and shopping becoming ubiquitous, ensuring the privacy of the users of such services has become a requirement in order to build and maintain customer trust. While text privatization methods exist, they require the existence of a trusted party that collects user data before applying a privatization method to preserve users' privacy. In this work we propose an efficient mechanism to provide metric differential privacy for text data on-device. With our solution, sensitive data never leaves the device and service providers only have access to privatized data to train models on and analyze. We compare our algorithm to the state-of-the-art for text privatization, showing similar or better utility for the same privacy guarantees, while reducing the storage costs by orders of magnitude, enabling on-device text privatization.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes