Dies ist eine Übersichtsseite mit Metadaten zu dieser wissenschaftlichen Arbeit. Der vollständige Artikel ist beim Verlag verfügbar.
Towards a Toolbox for Privacy-Preserving Computation on Health Data
0
Zitationen
3
Autoren
2022
Jahr
Abstract
Substantial advances in methods of collecting and aggregating large amounts of biomedical data have been met with insufficient measures of protecting it from unwarranted access and use. Most of the current layers of protection are merely aimed at ensuring compliance with regulations (e.g., the EU's General Data Protection Regulation) but do not represent a vision of privacy-by-design as an efficient and ethical advantage in biomedical research and clinical applications. This not only slows down the pace of such efforts but also leaves the data exposed to a wide spectrum of cyberattacks. This work presents an overview of recent advancements in data and compuation security, along with a discussion of their limitations and potential for deployement in both health care and research settings.
Ähnliche Arbeiten
k-ANONYMITY: A MODEL FOR PROTECTING PRIVACY
2002 · 8.418 Zit.
Calibrating Noise to Sensitivity in Private Data Analysis
2006 · 6.923 Zit.
Deep Learning with Differential Privacy
2016 · 5.655 Zit.
Federated Machine Learning
2019 · 5.627 Zit.
Communication-Efficient Learning of Deep Networks from Decentralized\n Data
2016 · 5.601 Zit.