Dies ist eine Übersichtsseite mit Metadaten zu dieser wissenschaftlichen Arbeit. Der vollständige Artikel ist beim Verlag verfügbar.
Phantom Anonymization: Adversarial testing for membership inference risks in anonymized health data
0
Zitationen
8
Autoren
2025
Jahr
Abstract
Our framework provides an empirical way to assess residual membership inference risks for a wide range of anonymization methods. As it adopts a technique developed for synthetic data, it also enables comparisons of residual risks between synthetic and anonymized datasets.
Ähnliche Arbeiten
k-ANONYMITY: A MODEL FOR PROTECTING PRIVACY
2002 · 8.402 Zit.
Calibrating Noise to Sensitivity in Private Data Analysis
2006 · 6.895 Zit.
Deep Learning with Differential Privacy
2016 · 5.629 Zit.
Communication-Efficient Learning of Deep Networks from Decentralized\n Data
2016 · 5.595 Zit.
Federated Machine Learning
2019 · 5.581 Zit.