PhD student position in privacy-preserving federated learning

Federated learning is revolutionizing the way in which machine learning models are trained and deployed. It holds great promise in unlocking the full potential of AI in various domains, including healthcare, finance, autonomous driving, smart cities, and satellite networks. Joining our ambitious and dynamic team focused on federated learning will provide you with the opportunity to work with a wide network of international collaborators, enabling you to make a significant impact in this rapidly-evolving field.

Information about the division and the department
At the Department of Electrical Engineering, we conduct internationally renowned research in artificial intelligence, information and communication theory, biomedical engineering, signal processing, and image analysis. We offer a dynamic and international research environment with about 150 employees from more than 20 countries, and with extensive national and international research collaborations with academia, industry and society. The department provides more than 70 advanced courses for Ph.D. students. Read more at our website.

Project description
Conventional machine learning approaches require centralizing all the data in the cloud. However, gathering the data at a central location requires data owners to give up control over their data, resulting in severe privacy and security risks. To address these shortcomings, federated learning is a recent machine learning paradigm that relies on the idea that knowledge (realized as trained models or gradients), instead of the raw data, should be shared. Federated learning faces two major challenges: The vulnerability of models and gradients to inference attacks, which jeopardize user's privacy, and the risk of poisoning attacks, where malicious or faulty clients can corrupt the global model by injecting mislabeled training data or modifying local model updates. The adoption of federated learning in sensitive applications such as healthcare, finance, or autonomous driving, depends on suitably addressing these challenges. The overarching goal of this project is to mathematically quantify the privacy and security guarantees--and their trade-off--of federated learning.

This position is funded by the Wallenberg AI, autonomous systems, and software program (WASP), a major national initiative for strategic basic research, education, and faculty recruitment in artificial intelligence, and the largest individual research program in Sweden.

The selected candidate will be supervised by Prof. Alexandre Graell i Amat and Dr. Khac-Hoang Ngo at the Department of Electrical Engineering and will integrate an ambitious and dynamic team on decentralized learning currently consisting of two Ph.D. students and two postdocs. The hired student will join a vibrant and internationally renowned research team at Chalmers, conducting research spanning many fields and including theoretical machine learning, information and coding theory, and signal processing.

The selected candidate will also enjoy our close collaboration with AI Sweden, the Swedish national center for applied artificial intelligence, and will be co-supervised by Dr. Johan Östman at AI Sweden. The student will further take advantage of our current collaborations on decentralized learning with the Technical University of Munich (Germany), Aalto University (Finland), and Simula UiB (Norway).

Major responsibilities
In this project, you will lead and perform cutting-edge research on privacy- and security-preserving federated learning. You are expected to publish high-quality high-impact papers, work with other PhD students and senior researchers in the team.

Qualifications
PhD in Mathematics, Theoretical Physics, Computer Science, Electrical Engineering, or similar.
Applicants must have a strong background in mathematics. Knowlege about machine learning is an asset.

We look for candidates with a strong interest in pursuing theoretical research, who are independent, curious, and creative, and have the ability to work in an international environment and to present their ideas effectively.

Good programming skills (Python). Excellent English skills (written and oral).

Contract terms
The position is for 4 years. During the Ph.D., the student is also expected to teach for the equivalent of around 6 months, and the contract is extended accordingly (i.e., the total duration is around 4.5 years). You will receive a competitive salary (the starting gross salary is 32150 SEK/month and it increases during the duration of the Ph.D.) with healthcare, social benefits, and pension, and enjoy students' benefits (such as student housing).

We offer
Chalmers offers a cultivating and inspiring working environment in the coastal city of Gothenburg. 
Read more about working at Chalmers and our benefits for employees.

Chalmers aims to actively improve our gender balance. We work broadly with equality projects, for example the GENIE Initiative on gender equality for excellence. Equality and diversity are substantial foundations in all activities at Chalmers.

Application procedure
The application should be marked with Ref 20230289 and written in English. The application should be sent electronically and be attached as PDF-files, as below. Maximum size for each file is 40 MB. Please note that the system does not support Zip files.

CV:(Please name the document: CV, Family name, Ref. number)
• CV
• Other, for example previous employments or leadership qualifications and positions of trust.
• Two references that we can contact.

Personal letter:(Please name the document as: Personal letter, Family name, Ref. number)
1-3 pages where you:
• Introduce yourself
• Describe your previous experience of relevance for the position (e.g. education, thesis work and, if applicable, any other research activities)
• Describe your future goals and future research focus

Other documents:
• Copies of bachelor and/or master’s thesis.
• Attested copies and transcripts of completed education, grades and other certificates, e.g. TOEFL test results.

Please use the button at the foot of the page to reach the application form. 

Application deadline: [2023-05-31]

For questions, please contact:
Alexandre Graell i Amat, Department of Electrical Engineering,
alexandre.graell@chalmers.se