activity
20242026
collaborators

8 papers

eess.AS2026

Goodbye Equal Error Rate, Hello Local Information Disclosure: Evaluating Voice Anonymisation against 1-to-N Linkage Threats

Dāvis Šterns, Konstantinos Drossos, Natasha Fernandes +2

Voice anonymisation aims to protect speaker identity. Currently, its empirical privacy evaluation heavily relies on the Equal Error Rate (EER). Originally designed for biometric ve…

cs.CR2026

Beyond Epsilon: A Principled QIF Framework for Local Differential Privacy

Ramon G. Gonze, Natasha Fernandes, Heber H. Arcolezi +2

Local Differential Privacy (LDP) has become the de facto standard for privacy-preserving data collection in large-scale systems, in particular for the purpose of estimating frequen…

cs.CR2025

Composition Theorems for f-Differential Privacy

Natasha Fernandes, Annabelle McIver, Parastoo Sadeghi

"f differential privacy" (fDP) is a recent definition for privacy privacy which can offer improved predictions of "privacy loss". It has been used to analyse specific privacy mecha…

cs.CR2025

What is the Cost of Differential Privacy for Deep Learning-Based Trajectory Generation?

Erik Buchholz, Natasha Fernandes, David D. Nguyen +3

While location trajectories offer valuable insights, they also reveal sensitive personal information. Differential Privacy (DP) offers formal protection, but achieving a favourable…

cs.LG2025

Empirical Calibration and Metric Differential Privacy in Language Models

Pedro Faustini, Natasha Fernandes, Annabelle McIver +1

NLP models trained with differential privacy (DP) usually adopt the DP-SGD framework, and privacy guarantees are often reported in terms of the privacy budget . However, d…

cs.LG2025

Comparing privacy notions for protection against reconstruction attacks in machine learning

Sayan Biswas, Mark Dras, Pedro Faustini +4

Within the machine learning community, reconstruction attacks are a principal concern and have been identified even in federated learning (FL), which was designed with privacy pres…