DataSHIELD Conference, Liverpool, 6–9 October at Hope Street Hotel. Talks, training and networking.

*"Federated Analysis in R with DataSHIELD" presented by [Ahmet Akkoç](https://www.linkedin.com/in/ahmet-akkoc/) +* *"Browser-based R with Quarto-live" presented by [Rasmus

𝗪𝗵𝗼 𝘂𝘀𝗲𝘀 𝗗𝗮𝘁𝗮𝗦𝗛𝗜𝗘𝗟𝗗?   This summer DataSHIELD undergraduate Kathryn Ward joined the DataSHIELD research project, University of Liverpool as a…

DataSHIELD Conference, Liverpool, 6–9 October at Hope Street Hotel. Talks, training and networking.

DataSHIELD Conference, Liverpool, 6–9 October at Hope Street Hotel. Talks, training and networking.

AbstractSummary. Extensive human health data from cohort studies, national registries, and biobanks can reveal lifecourse risk factors impacting health. Co

DataSHIELD | 356 followers on LinkedIn. Taking analysis to the data | This page shares news and updates from the DataSHIELD open source community

Fine-tuning large language models (LLMs) on domain-specific datasets has become a standard paradigm for adapting LLMs to specialized applications. However, recent work has shown that even fine-tuning on benign task-specific data can substantially weaken the safety capabilities of LLMs. While existi…

Tools for wrapping 'DataSHIELD' analyses into RO-Crate (Research Object Crate) objects. Provides functions to create structured metadata for federated data analysis projects, enabling governance tracking of data access, project membership, analysis execution and output validation across distributed data sources.

Base 'DataSHIELD' functions for the client side. 'DataSHIELD' is a software package which allows you to do non-disclosive federated analysis on sensitive data. 'DataSHIELD' analytic functions have been designed to only share non disclosive summary statistics, with built in automated output checking based on statistical disclosure control. With data sites setting the threshold values for the automated output checks. For more details, see citation('dsBaseClient').