Protecting Trained Models in Privacy-Preserving Federated Learning
Find out how you can protect individual's data after it's been used in training models through output privacy.
Input privacy for vertical federated learning
Posted by:
Dave Buckley, Mark Durkee, Joe Near and David Darais, Posted on:
-
Categories:
Data, PETs Blogs
This post is part of a series on privacy-preserving federated learning. The series is a collaboration between the Responsible Technology Adoption Unit (RTA) and the US National Institute of Standards and Technology (NIST). Learn more and read all the posts …
Protecting Model Updates in Privacy-Preserving Federated Learning
Posted by:
David Darais and Joe Near, Posted on:
-
Categories:
Data, Data collection, Data-driven technology, Data-sharing, PETs Blogs
In our second post we described attacks on models and the concepts of input privacy and output privacy. ln our previous post, we described horizontal and vertical partitioning of data in privacy-preserving federated learning (PPFL) systems. In this post, we …
Privacy-Preserving Federated Learning: Understanding the Costs and Benefits
Posted by:
Sue Anie and Paul Comerford (ICO), Posted on:
-
Categories:
Data, Data collection, Data-driven technology, Data-sharing
Privacy Enhancing Technologies (PETs) could enable organisations to collaboratively use sensitive data in a privacy-preserving manner and, in doing so, create new opportunities to harness the power of data for research and development of trustworthy innovation. However, research DSIT commissioned …
The tide is changing: Monitoring public attitudes towards data and AI
Posted by:
Sylvie Hobden and Dea Begaj, Posted on:
-
Categories:
Algorithms, Artificial intelligence, Data, Data collection, Data-sharing, Decision-making, Demographic data, Diversity, Equity, Ethical innovation, Public engagement
Today marks the publication of the third wave of the Centre for Data Ethics and Innovation (CDEI) Public Attitudes to Data and AI tracker survey. The CDEI leads the Government’s work to enable trustworthy innovation using data and AI as …
Working with the ICO to encourage the adoption of PETs
Posted by:
Mahi Hardalupas, Posted on:
-
Categories:
Algorithms, Artificial intelligence, Data, Ethical innovation
Last year, the CDEI launched a responsible data access programme to address the challenges organisations face to access data they need in a responsible way. A key component of this programme is our work to encourage adoption of Privacy-Enhancing Technologies …
Improving responsible access to demographic data to address bias
Posted by:
Amy Dickens and Benjamin Moore, Posted on:
-
Categories:
Algorithms, Artificial intelligence, Bias, Data, Demographic data, Intermediaries, Trust
Following our review into bias in algorithmic decision-making, the CDEI has been exploring challenges around access to demographic data for detecting and mitigating bias in AI systems, and considering potential solutions to address these challenges. Today we are publishing our …
Edwina Dunn: Reflections from the CDEI Advisory Board
Posted by:
Edwina Dunn, Posted on:
-
Categories:
Algorithms, Artificial intelligence, Assurance, Data, Responsible innovation, Trust, Trustworthy innovation
I have long believed in the power of data to make a meaningful difference to people's lives. Working in the field for over 30 years, I have seen the ways in which data can be used as a powerful force …
Developing the Algorithmic Transparency Standard in the open
Posted by:
Elena Hess-Rheingans, Central Digital and Data Office and Lara Bird, Centre for Data Ethics and Innovation, Posted on:
-
Categories:
Algorithms, Transparency, Trustworthy innovation
Today the Central Digital and Data Office (CDDO) and the Centre for Data Ethics and Innovation (CDEI) are sharing an updated version of the Algorithmic Transparency Standard on GitHub. Sharing the updated Standard on GitHub will allow interested stakeholders to …
Part two: Examining public attitudes towards Smart Data schemes
Posted by:
Benjamin Moore, Wiktoria Kulik, CDEI, Hannah Spiro, CDEI, Holly Clarke, CDEI and Vincenzo Rampulla, BEIS, Posted on:
-
Categories:
Data, Public engagement, Trustworthy innovation
We have been working with the Department for Business, Energy, and Industrial Strategy (BEIS) to identify the features of ethical and trustworthy Smart Data schemes. Smart Data refers to the “secure sharing of customer data with authorised third party providers …
Recent Comments