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. Read more..
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. Read more..
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 Read more..
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. Read more..
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. Read more..
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. Read more..
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. Read more..
SIESTA Video Series: Text Anonymization on Sensitive Data
The SIESTA Video Series brings together a set of short videos in which several of the project’s use cases present their work and main objectives. In particular, the use cases on Medical Imaging, Energy Domain, Text Anonymization on sensitive data, and Demography have contributed to this series, each explaining their respective activities within the project.… Read more..
Second day of the 2nd EOSC-SIESTA All Hands Meeting
The second day of the 2nd EOSC-SIESTA All Hands Meeting focused on addressing several topics that remained open from the previous day and consolidating the outcomes of the collaborative sessions held during the meeting. The morning began with an update on the integration status of the project’s use cases, where partners shared progress following the… Read more..
EOSC-SIESTA holds the first day of its 2nd All Hands Meeting
The EOSC-SIESTA consortium met for the first day of the 2nd All Hands Meeting, bringing together project partners to review progress and coordinate the next steps of the project. The meeting began with an overview of the current status of EOSC-SIESTA, including updates on deliverables, milestones and financial aspects. This session helped partners align the… Read more..
