7 papers
Bayesian Membership Privacy for Graph Neural Networks
Sinan Yıldırım, Megha Khosla
Existing privacy analyses for Graph Neural Networks (GNNs) largely inherit assumptions from non-graph settings, overlooking structural correlations and stochastic training-graph sa…
Multiple Jump MCMC: A Scalable Algorithm for Bayesian Inference on Binary Model Spaces
Lucas Vogels, Reza Mohammadi, Marit Schoonhoven +2
This article considers Bayesian model inference on binary model spaces. Binary model spaces are used by a large class of models, including graphical models, variable selection, mix…
Learning with Subset Stacking
Å. Ä°lker Birbil, Sinan Yıldırım, Samet Ãopur +1
We propose a new regression algorithm that learns from a set of input-output pairs. Our algorithm is designed for populations where the relation between the input variables and the…
Rényi Differential Privacy for Heavy-Tailed SDEs via Fractional Poincaré Inequalities
Benjamin Dupuis, Mert Gürbüzbalaban, Umut ÅimÅekli +3
Characterizing the differential privacy (DP) of learning algorithms has become a major challenge in recent years. In parallel, many studies suggested investigating the behavior of…
Privacy of SGD under Gaussian or Heavy-Tailed Noise: Guarantees without Gradient Clipping
Umut ÅimÅekli, Mert Gürbüzbalaban, Sinan Yıldırım +1
The injection of heavy-tailed noise into the iterates of stochastic gradient descent (SGD) has garnered growing interest in recent years due to its theoretical and empirical benefi…
MCMC for Bayesian estimation of Differential Privacy from Membership Inference Attacks
Ceren Yildirim, Kamer Kaya, Sinan Yildirim +1
We propose a new framework for Bayesian estimation of differential privacy, incorporating evidence from multiple membership inference attacks (MIA). Bayesian estimation is carried…