Gaussian Di ↵ erential Privacy

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Auditing Differentially Private Machine Learning: How Private is Private SGD? (2020, background): “Indeed a big part of making diﬀerentially private machine learning practical has been the signiﬁcant body of work giving progressively more reﬁned privacy analyses speciﬁcally for DP-SGD [ACG + 16, DRS19, MTZ19, YLP + 19], and for all we know these bounds on ε will continue to shrink.”
Element Level Differential Privacy: The Right Granularity of Privacy (2019, unknown): “The substantial growth in data collection across many domains has led to commensurate attention to and work on privacy risks in both academic [Dwork et al. 2006b, Dwork and Roth 2014] and industrial settings [Erlings-son, Pihur, and Korolova 2014, Apple Differential Privacy Team 2017, Bhowmick et al”
Deep Learning with Gaussian Differential Privacy (2019, unknown): “One possible candidate is f - diﬀerential privacy , a relaxation of ( ε, δ )-DP that was recently proposed by Dong, Roth, and Su [17].”
Hypothesis Testing Interpretations and Renyi Differential Privacy (2019, methodology): “Gaussian di ﬀ erential privacy (GDP) [Dong et al., 2019, Def.”