Postdoc position in the research group in distributed system at the Department of Computing science at Umeå University.
Project description and working tasks
The rapid increase of autonomous systems, connected devices, and distributed applications pose challenges in dealing with petabytes of data in diverse resource-constrained environments. Federated machine learning (FML) is collaborative learning to handle these problems without sharing data with centralised servers. However, several emerging threats target FML training, learning, and inference to fail or mislead models at early learning rounds. Attackers aim to break trustworthiness under different threat models, such as insiders-outsiders attacks, semi-honest or fully malicious participants, and attacks in training, learning, or inference phases. As a result, the learning models fail to provide acceptable performance. Therefore, this project aims to develop and implement trustworthy federated learning algorithms for limited and diverse non-iid (independent identically distributed) data under non-standard and adversarial settings, which are ideally suited for constraint environments and edge computing infrastructures. These goals can be achieved by inducing unique features in federated learning algorithms such as decentralised training, optimal device selection, secure learning and inference, fault-tolerance against failures and attacks, as well as resilient, fair and robust models. The ambition is to validate them in classical non-standard settings and apply them to solutions for constraint environments (e.g., Internet of Things (IIoT), healthcare systems, robotics) and edge infrastructures. Potentially, teaching up to a maximum of 20% can be included in the work tasks.