Cybersecure machine learning on open infrastructure
Modern machine learning offers opportunities for advanced data analysis in many different applications in society and industry, enabling more efficient responses to crises, improving processes and product safety, or decreasing environmental impact. Implementing such solutions on open infrastructure eliminates the need for expensive, dedicated infrastructure. However, these opportunities are also accompanied by fundamental cybersecurity threats: Transferring data to the open infrastructure means that the data is subject to a (foreign) third-party’s security measures and becomes vulnerable to data breaches, espionage, and possibly foreign legislation.
This project addresses this challenge by developing secure, privacy-preserving machine learning methods that ensure full data protection, preventing espionage, and ensuring full privacy.
Project leader: Roland Hostettler
Co-investigators: Anders Ahlén, Subhrakanti Dey
Funding period: 2021-2024
Project-ID: 2021-06334_VR
More information about the project in the Swecris database
Scalable and secure distributed computation networks
The aim of this project is to develop secure and scalable distributed computation networks based on AI-in-a-box computation nodes for secure, privacy-preserving, and scalable machine learning on open infrastructure. This is achieved by leveraging a combination of homomorphic encryption, differential privacy, as well as federated learning.
Project leader: Roland Hostettler
Funding period:1 June 2023–31 May 2026
Project-ID: 2023-00236_Vinnova
More information about the project in the Swecris database
Bayesian federated learning for spatio-temporal systems
Spatio-temporal processes are ubiquitous in nature, science, and engineering. With recent advances in sensor technology and the widespread adoption of, for example, mobile and 5G internet of things devices, cost-efficient large-scale data collection and processing of such processes has become feasible.
However, exploiting these opportunities faces several challenges, including privacy issues and limitations in the energy budget, computational power, and connectivity of the participating devices.
This project addresses these challenges by developing a new framework for machine learning in spatio-temporal systems that takes these limitations into account.
Project leader: Roland Hostettler
Funding period: 2023-2026
Project-ID: 2022-04505_VR
More information about the project in the Swecris database
