Postdoctoral position in Machine Learning focusing on Secure Federated Learning - Hiring in process/Finished, not possible to apply

Are you interested in working with machine learning and distributed algorithms, with the support of competent and friendly colleagues in an international environment? Are you looking for an employer that invests in sustainable employeeship and offers safe, favourable working conditions? We welcome you to apply for a postdoctoral position at Uppsala University.

The Department of Information Technology holds a leading position in both research and education at all levels. We are currently Uppsala University's third largest department, have around 350 employees, including 120 teachers and 120 PhD students. Approximately 5,000 undergraduate students take one or more courses at the department each year. You can find more information about us on the department of Information Technology website.

At the Division of Systems and Control, which belongs to the Department of Information Technology, we develop both theory and concrete tools to design systems that learn, reason, and act in the real world based on a seamless combination of data, mathematical models, and algorithms. Our research integrates expertise from control theory, machine learning, optimization, and network science, spanning diverse application domains such as energy systems, biomedical systems, neuroscience, and safety and security.

The Division of Systems and Control enjoys a wide network of strong international collaborators all around the world, for example at the Delft University of Technology, University of Cambridge, University of Oxford, Imperial College, University of British Columbia, University of Sydney, University of Newcastle and Aalto University. There are also ample opportunities for collaborations with other leading machine learning groups in Sweden and Europe, through our affiliations with WASP and the ELLIS society, respectively.

Duties
This position is part of a joint project on secure federated learning funded by the Swedish Agency for Innovation Systems (Vinnova) and led by Scaleout Systems AB together with Uppsala University. The postdoctoral researcher will be jointly supervised by Associate Prof. André Teixeira (Uppsala University) and Salman Toor (CTO at Scaleout, Associate Prof. at Uppsala University).

In this project, our focus will be on security and privacy-enhancing techniques for federated machine learning. The approach is centered around developing new theories and methodologies to achieve secure aggregation of federated machine learning models. The first goal here is to better understand how to algorithmically handle late and sampling-based model updates in practice in a way that allows for scalability yet introduces minimal model bias. In particular, we are interested in understanding how client sampling, model partitioning, and aggregation strategies affect and can be integrated into formal security analysis. From this new understanding, we aim to co-design the training process and the architecture and aggregation strategies in order to ensure model integrity with high probability in adversarial contexts.

The precise research scope will be decided in a dialog between the candidate and the supervisors after a successful appointment. The position might also include teaching in related subjects (max 20%).

The successful candidate will join the research group Secure Learning and Control Laboratory at Uppsala University, a growing interdisciplinary research group doing basic and applied research at the intersection of cybersecurity, control theory, and machine learning. Our vision is to develop methodologies for designing intelligent autonomous decision-making systems that are secure and resilient against malicious adversaries and natural failures.

Requirements
PhD degree in a field closely related to this position, such as computational mathematics, machine learning, automatic control, optimization, signal processing, or a foreign degree equivalent to a PhD degree in either of the aforementioned fields. The degree needs to be obtained by the time of the decision of employment. Those who have obtained a PhD degree three years prior to the application deadline are primarily considered for the employment. The starting point of the three-year frame period is the application deadline. Due to special circumstances, the degree may have been obtained earlier. The three-year period can be extended due to circumstances such as sick leave, parental leave, duties in labour unions, etc.

The applicant must have a strong background in method development and the use of algorithmic machine learning and stochastic optimization algorithms. Additional requirements for this position include proficiency in programming (preferably in Python), as well as knowledge of computer science, with a focus on one of the following subjects: distributed systems, optimization, or machine learning.

Publications at leading conferences in machine learning and/or leading conferences and journals in computational mathematics (for instance statistics or optimization) are a strong plus.

As a person, you are creative, thorough, and have a structured approach. When selecting among the applicants we will assess their ability to independently drive their work forward, to collaborate with others, to have a professional approach, and to analyze and work with complex problems. Great emphasis will be placed on personal characteristics and personal suitability. Excellent knowledge of oral and written English is a requirement.

Additional qualifications
Additionally, experience of interdisciplinary research is a merit. Experience and courses in one or more of the following subjects is valued: statistical machine learning, distributed optimization, and stochastic algorithms. For this project, we also value knowledge in security and privacy.

Application
The application must contain:

1. A curriculum vitae (CV);
2. A copy of relevant degrees and grade documents (translated into Swedish or English);
3. A list of publications;
4. Up to five selected publications in electronic format;
5. A research statement describing your past and current research (max 1 page) and a proposal for future activities (max 1 page). The statement should explain how your profile fits the position;
6. Contact information for two references (name, e-mail, and phone number);
7. A cover letter briefly describing your motivation for applying for this position and the earliest possible employment date (max 1 page).

About the employment
The employment is a temporary position of 2 years according to central collective agreement. Full time position. Starting date as soon as possible or as agreed. Placement: Uppsala.

For further information about the position, please contact: Associate Professor André Teixeira (phone: +46  18-471 5414, email: andre.teixeira@it.uu.se).

Please submit your application by 18 April 2024, UFV-PA 2024/791.

Are you considering moving to Sweden to work at Uppsala University? Find out more about what it´s like to work and live in Sweden.