Privacy-Protected Machine Learning for Transport Systems
Research Project, 2020
– 2021
This interdisciplinary project addresses forward-looking challenges in machine learning (ML) using prevailing and methodologies from the areas of computer security and distributed systems. Current ML implementations often need to collect a large amount of information that can be privacy-sensitive, before applying ML algorithms. It is a common practice to sanitize such privacy-sensitive information. However, there were numerous reports about cases in which by combining sanitized datasets turned out to violate privacy requirements. This project will seek to develop privacy-protected manipulation-resilient ML solutions. The project will provide imperative privacy-preserving analytics tools needed for working with ML in the automotive industry.
Participants
Elad Schiller (contact)
Chalmers, Computer Science and Engineering (Chalmers), Networks and Systems (Chalmers)
Irene Yu-Hua Gu
Chalmers, Electrical Engineering
Tomas Olovsson
Chalmers, Computer Science and Engineering (Chalmers), Networks and Systems (Chalmers)
Shiliang Zhang
Chalmers, Computer Science and Engineering (Chalmers), Networks and Systems (Chalmers)
Collaborations
Chalmers AI Research Centre (CHAIR)
Gothenburg, Sweden
Funding
AoA Transport Funds
Funding Chalmers participation during 2020–2021
Related Areas of Advance and Infrastructure
Transport
Areas of Advance