# Topology-aware Differential Privacy for Decentralized Image Classification

arXiv: https://arxiv.org/abs/2006.07817 · HTML: https://mlsanity.com/paper/2006.07817/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jun 2020.

## Built on by (most cited first, 6 of 6)

- [Sentinel-Guided Zero-Shot Learning: A Collaborative Paradigm without Real Data Exposure](https://mlsanity.com/paper/2403.09363/) (2024)
- [Ownership Verification of DNN Architectures via Hardware Cache Side Channels](https://mlsanity.com/paper/2102.03523/) (2021)
- [Privacy-Preserving Distributed Optimization and Learning](https://mlsanity.com/paper/2403.00157/) (2024)
- [Contextualize differential privacy in image database: a lightweight image differential privacy approach based on principle component analysis inverse](https://mlsanity.com/paper/2202.08309/) (2022)
- [Privacy-Preserving, Dropout-Resilient Aggregation in Decentralized Learning](https://mlsanity.com/paper/2404.17984/) (2024)
- [TSDCRF: Balancing Privacy and Multi-Object Tracking via Time-Series CRF and Normalized Control Penalty](https://mlsanity.com/paper/2603.13667/) (2026)

## Abstract (arXiv)

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.