Privacy-Preserving and Attack-Resistant Learning at the Edge

This project aims to develop a blockchain-enhanced federated learning (FL) framework to secure edge computing applications in critical sectors such as healthcare, transportation, and manufacturing. These domains demand robust protection of privacy, data integrity, and resilience against cyber threats. By integrating FL, blockchain, and graph-based modelling, the project will generate new knowledge in privacy-preserving, attack-resistant learning systems deployed at the edge. Led by Professor Hua Wang and Dr Jiao Yin, the supervisory team brings deep expertise in AI, cybersecurity, and distributed systems. We are seeking highly motivated PhD applicants with a background in computer science, cybersecurity, or data science. Prior experience with federated learning, blockchain, or edge computing, supported by strong research publications, is desirable. The successful candidate will develop scalable and trustworthy algorithms that advance Australia’s digital transformation and protect critical infrastructure.