Balázs Pejó

SoK: Differential privacies

2020 · Proceedings on Privacy Enhancing Technologies

Abstract Shortly after it was first introduced in 2006, differential privacy became the flagship data privacy definition. Since then, numerous variants and extensions were proposed to adapt it to different scenarios and attacker models. In …

Property Inference Attacks on Convolutional Neural Networks: Influence and Implications of Target Model’s Complexity

2021

Machine learning models' goal is to make correct predictions for specific tasks by learning important properties and patterns from data. By doing so, there is a chance that the model learns properties that are unrelated …