no code implementations • 7 Feb 2024 • Marlon Tobaben, Gauri Pradhan, Yuan He, Joonas Jälkö, Antti Honkela
We apply a state-of-the-art membership inference attack (MIA) to systematically test the practical privacy vulnerability of fine-tuning large image classification models. We focus on understanding the properties of data sets and samples that make them vulnerable to membership inference.
no code implementations • 15 Dec 2023 • Rubèn Tito, Khanh Nguyen, Marlon Tobaben, Raouf Kerkouche, Mohamed Ali Souibgui, Kangsoo Jung, Lei Kang, Ernest Valveny, Antti Honkela, Mario Fritz, Dimosthenis Karatzas
We employ a federated learning scheme, that reflects the real-life distribution of documents in different businesses, and we explore the use case where the ID of the invoice issuer is the sensitive information to be protected.
1 code implementation • 16 Mar 2023 • Bobby Huggins, Chengkun Li, Marlon Tobaben, Mikko J. Aarnos, Luigi Acerbi
PyVBMC is a Python implementation of the Variational Bayesian Monte Carlo (VBMC) algorithm for posterior and model inference for black-box computational models (Acerbi, 2018, 2020).
1 code implementation • 2 Feb 2023 • Marlon Tobaben, Aliaksandra Shysheya, John Bronskill, Andrew Paverd, Shruti Tople, Santiago Zanella-Beguelin, Richard E Turner, Antti Honkela
There has been significant recent progress in training differentially private (DP) models which achieve accuracy that approaches the best non-private models.
1 code implementation • 30 Sep 2022 • Antti Koskela, Marlon Tobaben, Antti Honkela
In order to account for the individual privacy losses in a principled manner, we need a privacy accountant for adaptive compositions of randomised mechanisms, where the loss incurred at a given data access is allowed to be smaller than the worst-case loss.