Topology-aware Differential Privacy for Decentralized Image Classification

TL;DR

This paper introduces Top-DP, a topology-aware differential privacy method for decentralized image classification that reduces noise and enhances model usability by leveraging communication topology features.

Contribution

It presents a novel topology-aware noise reduction strategy integrated with DP-SGD and two new learning protocols tailored for different network topologies.

Findings

Achieves better privacy-utility trade-off than prior methods

Proves formal DP guarantees for the proposed protocols

Demonstrates improved model usability in experiments

Abstract

In this paper, we design Top-DP, a novel solution to optimize the differential privacy protection of decentralized image classification systems. The key insight of our solution is to leverage the unique features of decentralized communication topologies to reduce the noise scale and improve the model usability. (1) We enhance the DP-SGD algorithm with this topology-aware noise reduction strategy, and integrate the time-aware noise decay technique. (2) We design two novel learning protocols (synchronous and asynchronous) to protect systems with different network connectivities and topologies. We formally analyze and prove the DP requirement of our proposed solutions. Experimental evaluations demonstrate that our solution achieves a better trade-off between usability and privacy than prior works. To the best of our knowledge, this is the first DP optimization work from the perspective of network topologies.