Correlated Privacy Mechanisms for Differentially Private Distributed Mean Estimation
Vithana, Sajani, Cadambe, Viveck R., Calmon, Flavio P., Jeong, Haewon
–arXiv.org Artificial Intelligence
Differentially private distributed mean estimation (DP-DME) is a fundamental building block in privacy-preserving federated learning, where a central server estimates the mean of $d$-dimensional vectors held by $n$ users while ensuring $(\epsilon,\delta)$-DP. Local differential privacy (LDP) and distributed DP with secure aggregation (SecAgg) are the most common notions of DP used in DP-DME settings with an untrusted server. LDP provides strong resilience to dropouts, colluding users, and malicious server attacks, but suffers from poor utility. In contrast, SecAgg-based DP-DME achieves an $O(n)$ utility gain over LDP in DME, but requires increased communication and computation overheads and complex multi-round protocols to handle dropouts and malicious attacks. In this work, we propose CorDP-DME, a novel DP-DME mechanism that spans the gap between DME with LDP and distributed DP, offering a favorable balance between utility and resilience to dropout and collusion. CorDP-DME is based on correlated Gaussian noise, ensuring DP without the perfect conditional privacy guarantees of SecAgg-based approaches. We provide an information-theoretic analysis of CorDP-DME, and derive theoretical guarantees for utility under any given privacy parameters and dropout/colluding user thresholds. Our results demonstrate that (anti) correlated Gaussian DP mechanisms can significantly improve utility in mean estimation tasks compared to LDP -- even in adversarial settings -- while maintaining better resilience to dropouts and attacks compared to distributed DP.
arXiv.org Artificial Intelligence
Jul-3-2024
- Country:
- North America > United States > California (0.14)
- Genre:
- Research Report > New Finding (0.54)
- Industry:
- Information Technology > Security & Privacy (1.00)
- Technology:
- Information Technology
- Artificial Intelligence > Machine Learning (1.00)
- Communications > Networks (0.92)
- Security & Privacy (1.00)
- Information Technology