Search results for: “”
FAIR for Sensitive Data
This result focuses on understanding how the FAIR principles can be applied to sensitive data. FAIR stands for Findable, Accessible, Interoperable and Reusable, and these principles help make digital objects easier to discover, access, combine and reuse. However, sensitive data cannot always follow the same approach as fully open data. In areas such as health,…
Best practices for sharing sensitive data
This result focuses on developing clear and practical recommendations for sharing sensitive data in a safe, responsible and useful way. Sensitive data can have great value for research, but it cannot always be shared openly. Legal requirements, privacy risks, ethical concerns and institutional rules often limit how these data can be accessed and reused. EOSC-SIESTA…
Trusted Data Spaces
This result focuses on creating trusted data spaces within the European Open Science Cloud, where sensitive data can be accessed, analysed and reused under clear security, privacy and governance conditions. The main idea is to provide controlled environments in which different organisations, researchers and data providers can collaborate without needing to openly expose the original…
Secure environments for sensitive data
This result focuses on the development of a secure cloud-based environment where sensitive data can be analysed without requiring users to download or directly handle the original datasets. Instead of moving data across different systems, researchers can access controlled environments where analysis can be performed under defined security, privacy and governance conditions. A key objective…
Key results
EOSC-SIESTA develops practical solutions to support the secure analysis, sharing and reuse of sensitive data within the European Open Science Cloud. In many research areas, such as health, epidemiology, social sciences or energy, data cannot simply be made openly available due to privacy, legal or ethical constraints. However, this does not mean that these data…
New EOSC-SIESTA publication: privacy-preserving Federated Learning in medical imaging
A new EOSC-SIESTA publication by IFCA-CSIC, INRIA, and TU Delft explores privacy protection in Federated Learning using sensitive medical imaging data. The study proposes a metric-privacy-inspired noise calibration strategy that improves global model accuracy while defending against Client Inference Attacks.
Siesta Concepts: Open Science
Open Science promotes a transparent and collaborative research ecosystem, driven by Europe’s EOSC initiative. However, sharing sensitive data requires balancing openness with privacy. EOSC-SIESTA addresses this challenge by developing trusted, cloud-based environments and privacy-preserving tools that make sensitive data securely shareable and usable under FAIR principles.
Discover UC3 Energy Domain Tool: optimising solar battery management in EOSC-SIESTA
EOSC-SIESTA addresses the challenge of analyzing sensitive data without compromising privacy through its energy domain use case (UC3). Focusing on solar installations, the project utilizes trusted execution environments and anonymization techniques to secure sensitive household consumption dat
Science Europe’s 40 members rally behind EOSC Partnership in FP10
Science Europe, representing 40 major research organizations, has issued a position statement urging a robust framework under the EU’s next FP10 programme to secure the future of EOSC.
Discover pyCANON: assessing dataset anonymity in EOSC-SIESTA
pyCANON is an open-source Python library and web application developed within EOSC-SIESTA to assess the anonymity and privacy risks of tabular datasets. Integrated into the project’s dashboard, it evaluates data against key anonymity models like k-anonymity and l-diversity, enabling researchers to make informed decisions before sharing sensitive information.
Siesta Concepts #2: Anonymization
Data anonymization transforms sensitive datasets to prevent individual identification while keeping data useful. Within EOSC-SIESTA, two open-source tools help researchers sanitize quasi-identifiers and assess privacy risks by applying advanced anonymity models (like k-anonymity and l-diversity) to protect sensitive tabular data.
SIESTA CONCEPTS#1: Federated Learning
Federated Learning (FL) allows multiple participants to collaboratively train AI models by keeping data local and sharing only encrypted model updates. Through the SIESTA dashboard, users can easily deploy secure FL clients, which connect to a central coordinating server hosted on AI4EOSC via the Flower framework and secure gRPC protocols, enabling privacy-preserving collaboration.