Dr. Xiaoning (Maggie) Liu
Details
-
College: School of Computing Technologies
-
Department: School of Computing Technologies
-
Campus: City Campus Australia
-
xiaoning.liu@rmit.edu.au
-
ORCID: 0000-0002-9874-8839
Open to
- Masters Research or PhD student supervision
About
I am a Lecturer (US Assistant Professor equivalent) at the School of Computing Technologies, RMIT University. I earned my Ph.D. degree in Computer Science from RMIT University. My research pivots on building and researching secure systems to address data privacy and security issues in machine learning. I am always looking for self-motivated students aiming for strong research! Please email me your CV, transcript, research statement, English test score.
My current research focuses on secure multi-party computation and its applications in privacy-preserving machine learning. My goal is to build impactful work that is expected to push forward the deployment of PPML on practical usages like medical diagnostics and mobile image classification.
My design philosophy is:
- Devising lightweight and fundamental secure computation protocols resort to advanced cryptographic techniques. I am particularly interested in secure multiparty computation, function secret sharing, zero knowledge proof.
- Building secure and practical PPML systems that harness the insights from computer systems, cryptography, machine learning. I conduct interdisciplinary research empowering versatile real-world service scenarios, like MLaaS (MediSC, CryptMed, OblivGNN), outsourced cloud computation (Sonic, EncSIM), mobile-edge computing (Leia), collaborative computation over distributed data ([ESORICS'19], [TDSC'20]).
More details can be found on my personal website https://maggichk.github.io/
Supervisor projects
- Leveraging Computer Vision-Informed Strategies for Large-Scale Language Models and Multimodal Backdoor Learning Defence
- 7 May 2024
- Privacy-Preserving Fairness Verification for Graph Neural Networks
- 13 Nov 2023
- Machine Unlearning
- 26 Oct 2023
- Cross Domain Searchable Encryption
- 13 Sep 2023
- Privacy-Preserving Collaborative Learning Over Medical Data
- 8 Nov 2022
Research interests
My current research focuses on secure multi-party computation and its applications in privacy-preserving machine learning. My goal is to build impactful work that is expected to push forward the deployment of PPML on practical usages like medical diagnostics and mobile image classification.
My design philosophy is:
- Devising lightweight and fundamental secure computation protocols resort to advanced cryptographic techniques. I am particularly interested in secure multiparty computation, function secret sharing, zero knowledge proof.
- Building secure and practical PPML systems that harness the insights from computer systems, cryptography, machine learning. I conduct interdisciplinary research empowering versatile real-world service scenarios, like MLaaS (MediSC, CryptMed, OblivGNN), outsourced cloud computation (Sonic, EncSIM), mobile-edge computing (Leia), collaborative computation over distributed data ([ESORICS'19], [TDSC'20]).
