3 papers
cs.IT2024
Chernoff Information as a Privacy Constraint for Adversarial Classification and Membership Advantage
Ayşe Ünsal
This work investigates a privacy metric based on Chernoff information motivated by its importance in characterizing the optimal classifier's performance. Adversarial classification…
cs.CR2023
Node Injection Link Stealing Attack
Oualid Zari, Javier Parra-Arnau, Ayşe Ünsal +1
In this paper, we present a stealthy and effective attack that exposes privacy vulnerabilities in Graph Neural Networks (GNNs) by inferring private links within graph-structured da…
cs.IT2022
Adversarial Classification under Gaussian Mechanism: Calibrating the Attack to Sensitivity
Ayse Unsal, Melek Onen
This work studies anomaly detection under differential privacy (DP) with Gaussian perturbation using both statistical and information-theoretic tools. In our setting, the adversary…