23 citations · 87 across the 23 of their papers we have counts for
24 papers
-Differential Privacy Filters: Validity and Approximate Solutions
Long Tran, Antti Koskela, Ossi Räisä +1
Accounting for privacy loss under fully adaptive composition -- where mechanism choice and privacy parameters may depend on the history of prior outputs -- is a central challenge i…
Accuracy-First Rényi Differential Privacy and Post-Processing Immunity
Ossi Räisä, Antti Koskela, Antti Honkela
The accuracy-first perspective of differential privacy addresses an important shortcoming by allowing a data analyst to adaptively adjust the quantitative privacy bound instead of…
Convex Approximation of Two-Layer ReLU Networks for Hidden State Differential Privacy
Rob Romijnders, Antti Koskela
The hidden state threat model of differential privacy (DP) assumes that the adversary has access only to the final trained machine learning (ML) model, without seeing intermediate…
Practical Differentially Private Hyperparameter Tuning with Subsampling
Antti Koskela, Tejas Kulkarni
Tuning the hyperparameters of differentially private (DP) machine learning (ML) algorithms often requires use of sensitive data and this may leak private information via hyperparam…
Individual Privacy Accounting with Gaussian Differential Privacy
Antti Koskela, Marlon Tobaben, Antti Honkela
Individual privacy accounting enables bounding differential privacy (DP) loss individually for each participant involved in the analysis. This can be informative as often the indiv…
Differentially Private Hamiltonian Monte Carlo
Ossi Räisä, Antti Koskela, Antti Honkela
Markov chain Monte Carlo (MCMC) algorithms have long been the main workhorses of Bayesian inference. Among them, Hamiltonian Monte Carlo (HMC) has recently become very popular due…