A comprehensive survey on local differential privacy
X Xiong, S Liu, D Li, Z Cai, X Niu - Security and Communication …, 2020 - Wiley Online Library
With the advent of the era of big data, privacy issues have been becoming a hot topic in
public. Local differential privacy (LDP) is a state‐of‐the‐art privacy preservation technique …
public. Local differential privacy (LDP) is a state‐of‐the‐art privacy preservation technique …
Advances and open problems in federated learning
Federated learning (FL) is a machine learning setting where many clients (eg, mobile
devices or whole organizations) collaboratively train a model under the orchestration of a …
devices or whole organizations) collaboratively train a model under the orchestration of a …
The distributed discrete gaussian mechanism for federated learning with secure aggregation
We consider training models on private data that are distributed across user devices. To
ensure privacy, we add on-device noise and use secure aggregation so that only the noisy …
ensure privacy, we add on-device noise and use secure aggregation so that only the noisy …
Shuffled model of differential privacy in federated learning
We consider a distributed empirical risk minimization (ERM) optimization problem with
communication efficiency and privacy requirements, motivated by the federated learning …
communication efficiency and privacy requirements, motivated by the federated learning …
Hiding among the clones: A simple and nearly optimal analysis of privacy amplification by shuffling
Recent work of Erlingsson, Feldman, Mironov, Raghunathan, Talwar, and Thakurta 1
demonstrates that random shuffling amplifies differential privacy guarantees of locally …
demonstrates that random shuffling amplifies differential privacy guarantees of locally …
The fundamental price of secure aggregation in differentially private federated learning
We consider the problem of training a $ d $ dimensional model with distributed differential
privacy (DP) where secure aggregation (SecAgg) is used to ensure that the server only sees …
privacy (DP) where secure aggregation (SecAgg) is used to ensure that the server only sees …
Scenario-based Adaptations of Differential Privacy: A Technical Survey
Differential privacy has been a de facto privacy standard in defining privacy and handling
privacy preservation. It has had great success in scenarios of local data privacy and …
privacy preservation. It has had great success in scenarios of local data privacy and …
Privacy amplification via compression: Achieving the optimal privacy-accuracy-communication trade-off in distributed mean estimation
Privacy and communication constraints are two major bottlenecks in federated learning (FL)
and analytics (FA). We study the optimal accuracy of mean and frequency estimation …
and analytics (FA). We study the optimal accuracy of mean and frequency estimation …
Private summation in the multi-message shuffle model
The shuffle model of differential privacy (Erlingsson et al. SODA 2019; Cheu et al.
EUROCRYPT 2019) and its close relative encode-shuffle-analyze (Bittau et al. SOSP 2017) …
EUROCRYPT 2019) and its close relative encode-shuffle-analyze (Bittau et al. SOSP 2017) …
Flame: Differentially private federated learning in the shuffle model
Federated Learning (FL) is a promising machine learning paradigm that enables the
analyzer to train a model without collecting users' raw data. To ensure users' privacy …
analyzer to train a model without collecting users' raw data. To ensure users' privacy …