PhD Scholarship in Privacy-Preserving Trustworthy Distributed Machine Learning Using Differential Privacy and Blockchain

Undertake two projects to develop scalable, differentially private approaches for distributed machine learning.

An opportunity for two talented students to undertake their PhDs on two projects that concentrate on developing differentially private approaches and blockchain-based solutions for privacy-preserving trustworthy distributed machine learning.

In this research, the successful candidates will focus on mathematical backgrounds involved in differential privacy to devise novel scalable approaches suitable for the privacy preservation of distributed machine learning scenarios such as federated learning, split learning, and distributed stochastic gradient descent. The existing differentially private machine learning approaches show issues in model performance and efficiency and vulnerability towards the application of noise over a large number of distributed models. These issues should be overcome by developing robust and feasible mathematical models for differential privacy by investigating the data dynamics (IID and Non-IID) of distributed machine learning. Besides, trustworthiness is another major property that needs to be investigated in distributed machine learning. Blockchain-based approaches are gaining much attention due to the inherent data immutability and trustworthiness properties offered by the underlying architectures. However, the high latency introduced by blockchain makes timely machine learning decision-making challenging. Hence, in this research, the students will also conduct thorough research in implementing feasible blockchain-based solutions to support trustworthy machine learning.

Up to $30,000 per year for 3 years as scholarship. The scholarship may be extended to 3.5 years depending on the progress.

To be eligible for this scholarship, you must:

  • Have maintained a high GPA (minimum of 3.70) score during an Honours degree in mathematics or computer science
  • Preference will be given to onshore students from RMIT University and other top-ranked universities
  • Must have research experience in mathematics or computer science
  • Must have programming skills in programming languages such as Matlab and Python
  • Preferably have a proven track record of good publications in mathematics or computer science
  • Preferably have research experience in mathematics or computer science.

Applicants should contact Associate Professor Ibrahim Khalil via ibrahim.khalil@rmit.edu.au and Professor Xun Yi xun.yi@rmit.edu.au with the following information to discuss eligibility:

  • A comprehensive CV
  • Degree certificates and academic transcripts
  • Evidence to prove previous research experience (top-ranked publications, preprints submitted to top-ranked journals, and working drafts)
  • Any letters of experience in research (e.g. recommendation letters from the previous research supervisor).

14 September 2020.

For further enquiries, please contact Associate Professor Ibrahim Khalil via ibrahim.khalil@rmit.edu.au and Professor Xun Yi via xun.yi@rmit.edu.au

aboriginal flag
torres strait flag

Acknowledgement of Country

RMIT University acknowledges the people of the Woi wurrung and Boon wurrung language groups of the eastern Kulin Nation on whose unceded lands we conduct the business of the University. RMIT University respectfully acknowledges their Ancestors and Elders, past and present. RMIT also acknowledges the Traditional Custodians and their Ancestors of the lands and waters across Australia where we conduct our business - Artwork 'Luwaytini' by Mark Cleaver, Palawa.