Tag: Sensitive Data Analytics
SIESTA Concepts #5: Named Entity Recognition
Sharing cyber incident reports aids threat detection, but they contain personal data that must be anonymised. Since the Named Entity Recognition models behind anonymisation are usually trained in English, EOSC SIESTA researchers tested them on Spanish and found that multilingual models trained on target-language reports work best.
SIESTA tool: DatLeak
DatLeak is a tool developed by the Neurobiology Research Unit (NRU) at Copenhagen University Hospital and available through the SIESTA Dashboard. It detects data leakage in anonymized datasets: when a dataset is randomized or scrambled, the resulting variables can still carry traces of the original values that could link a record back to a real…
SIESTA tool: BIDScramble
BIDScramble is an open-source tool developed by Radboud University within the EOSC-SIESTA project to facilitate the secure reuse of sensitive neuroimaging data. It transforms BIDS-formatted datasets into anonymous scrambled versions that maintain original structural and statistical properties.
SIESTA Tool: Dashboard
The EOSC-SIESTA Dashboard is the main interface connecting the project’s technical infrastructure with its practical research use cases. Based on Onyxia, this unified platform features a modular service catalog, MinIO S3-compatible storage, and a secure secret-management system, allowing researchers to safely access and analyze sensitive datasets.
3rd EOSC-SIESTA webinar: A journey through the SIESTA computing infrastructure
Discover the EOSC-SIESTA computing infrastructure on June 3, 2026. This third webinar offers a technical overview from the perspectives of providers, users, and developers, focusing on secure cloud environments, confidential computing, and sensitive data analytics.
SIESTA Tool: Text Anonymization on Sensitive Data
EOSC-SIESTA has developed a text anonymization tool prototype to securely share sensitive cyber incident reports. Created by Universidad de León, the tool uses AI and four anonymization techniques to mask confidential data, enabling safe data reuse for research, machine learning, and collaborative cyber defence.
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
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.