PhD/PostDoc Federated Learning and Blockchain
NEW (updated 19.04.2021)
The group is seeking TWO outstanding PhD students or PostDocs in the field of privacy-preserving deep federated learning using blockchain and smart contracts, particularly its mathematical foundations for operational and security analysis. The main objectives are i) to jointly develop a decentralized federated learning and trust management blockchain network architecture and the corresponding algorithms for supply chain purposes, and ii) to implement (together with partners) a proof of concept platform (cloud, smartphone, IoT sensors) which demonstrates the full learning capabilities comparable to centralized architecture for the mentioned use cases but complies with privacy and trust attributes from the blockchain network. The candidates are expected to develop a respective theoretical arsenal for performance and privacy guarantees as well as guiding the implementation process. For leveraging and testing the platform the partners have access to food-related IoT data from major food stakeholders which can be used or emulated within multiple IoT vertical silos.
Applicants must possess a master degree in computer science, mathematics, electrical engineering or similar, with i) profound theoretical knowledge in any of the above fields and ii) good coding skills in C, C++, Python, TensorFlow or PyTorch. Ability and willingness to work and cooperate with the members of group.
The candidate is expected to have a profound knowledge in the field of deep learning as well as good understanding of (information-theoretic, cryptographic) security. Applicants with additional skills in blockchain analysis (e.g. queueing theory or any other) will be given preference.
To be considered please send a short cover letter outlining your background, a detailed CV including possibly some references, and all relevant certificates to email@example.com (cc: firstname.lastname@example.org).
By submitting an online application, you agree to process and electronically store your data. Please note that the Free University of Berlin cannot take responsibility for the security of unprotected transmitted personal data send electronically.