Renyi Differential Privacy of the Subsampled Shuffle Model in Distributed Learning
We study privacy in a distributed learning framework, where clients collaboratively build a learning model iteratively through interactions with a server from whom we need privacy. Motivated by stochastic optimization and the federated learning (FL) paradigm, we focus on the case where a small fraction of data samples are randomly sub-sampled in each round to participate in the learning process, which also enables privacy amplification. To obtain even stronger local privacy guarantees, we study this in the shuffle privacy model, where each client randomizes its response using a local differentially private (LDP) mechanism and the server only receives a random permutation (shuffle) of the clients' responses without their association to each client. The principal result of this paper is a privacy-optimization performance trade-off for discrete randomization mechanisms in this sub-sampled shuffle privacy model. This is enabled through a new theoretical technique to analyze the Renyi Differential Privacy (RDP) of the sub-sampled shuffle model. We numerically demonstrate that, for important regimes, with composition our bound yields significant improvement in privacy guarantee over the state-of-the-art approximate Differential Privacy (DP) guarantee (with strong composition) for sub-sampled shuffled models. We also demonstrate numerically significant improvement in privacy-learning performance operating point using real data sets.
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningStochastic OptimizationSimilar Papers 제목 키워드 기반
On the Renyi Differential Privacy of the Shuffle Model
The central question studied in this paper is Renyi Differential Privacy (RDP) guarantees for general discrete local mechanisms in the shuffle privacy model. In the shuffle model, each of the $n$ clients randomizes its r…
Shuffle Gaussian Mechanism for Differential Privacy
We study Gaussian mechanism in the shuffle model of differential privacy (DP). Particularly, we characterize the mechanism's R\'enyi differential privacy (RDP), showing that it is of the form: $$ \epsilon(\lambda) \leq \…
Federated LearningOptimal Accounting of Differential Privacy via Characteristic Function
Characterizing the privacy degradation over compositions, i.e., privacy accounting, is a fundamental topic in differential privacy (DP) with many applications to differentially private machine learning and federated lear…
Federated LearningFunctional Renyi Differential Privacy for Generative Modeling
Differential privacy (DP) has emerged as a rigorous notion to quantify data privacy. Subsequently, Renyi differential privacy (RDP) becomes an alternative to the ordinary DP notion in both theoretical and empirical stud…
Privacy Amplification via Shuffled Check-Ins
We study a protocol for distributed computation called shuffled check-in, which achieves strong privacy guarantees without requiring any further trust assumptions beyond a trusted shuffler. Unlike most existing work, shu…
Federated Learning