13 citations · 20 across the 8 of their papers we have counts for
8 papers
On Reliability of Membership Inference Vulnerability Evaluation
Joonas Jälkö, Gauri Pradhan, Ossi Räisä +1
Membership inference attacks (MIAs) are popular methods for empirically assessing the leakage of sensitive information in the training data through models or statistics learned fro…
Noise-Aware Differentially Private Variational Inference
Talal Alrawajfeh, Joonas Jälkö, Antti Honkela
Differential privacy (DP) provides robust privacy guarantees for statistical inference, but this can lead to unreliable results and biases in downstream applications. While several…
Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning
Marlon Tobaben, Hibiki Ito, Joonas Jälkö +2
Membership inference attacks (MIAs) are used to test practical privacy of machine learning models. MIAs complement formal guarantees from differential privacy (DP) under a more rea…
Subsampling is not Magic: Why Large Batch Sizes Work for Differentially Private Stochastic Optimisation
Ossi Räisä, Joonas Jälkö, Antti Honkela
We study how the batch size affects the total gradient variance in differentially private stochastic gradient descent (DP-SGD), seeking a theoretical explanation for the usefulness…
On Consistent Bayesian Inference from Synthetic Data
Ossi Räisä, Joonas Jälkö, Antti Honkela
Generating synthetic data, with or without differential privacy, has attracted significant attention as a potential solution to the dilemma between making data easily available, an…
Noise-Aware Statistical Inference with Differentially Private Synthetic Data
Ossi Räisä, Joonas Jälkö, Samuel Kaski +1
While generation of synthetic data under differential privacy (DP) has received a lot of attention in the data privacy community, analysis of synthetic data has received much less.…
Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT
Antti Koskela, Joonas Jälkö, Lukas Prediger +1
We propose a numerical accountant for evaluating the tight -privacy loss for algorithms with discrete one dimensional output. The method is based on the privacy lo…
Differentially Private Variational Inference for Non-conjugate Models
Joonas Jälkö, Onur Dikmen, Antti Honkela
Many machine learning applications are based on data collected from people, such as their tastes and behaviour as well as biological traits and genetic data. Regardless of how impo…