Dr. Maggie Liu
Details
College: School of Computing Technologies
Department: School of Computing Technologies
Campus: City Campus Australia
xiaoning.liu@rmit.edu.au
Open to
- Masters Research or PhD student supervision
- Collaborative projects
- Industry Projects
- Membership of an advisory committee
About
I am a Senior Lecturer and an ARC Discovery Early Career Researcher Awardee (DECRA Fellow) at the School of Computing Technologies, RMIT University, Melbourne, Australia. I earned my Ph.D. degree in Computer Science at RMIT University in 2022. My research interests include secure computation, privacy-preserving machine learning, AI security and privacy. I am the recipient of the ARC DECRA Award 2026, the sole Best Paper Award of ESORICS 2021, the RMIT HDR Research Prize 2023. My work has appeared in prestigious venues in computer security, such as USENIX Security, NDSS, IEEE TDSC, TIFS. I have served on the technical program committee (TPC member) of USENIX Security, EuroS&P, ASIACCS, and the program co-chair of LAMPS at CCS 2025. I also serve as an Associate Editor for IEEE TSC.
Research fields
- 4604 Cybersecurity and privacy
- 460401 Cryptography
- 4611 Machine learning
- 4602 Artificial intelligence
UN sustainable development goals
- 9 Industry, Innovation and Infrastructure
- 12 Responsible Consumption and Production
- 4 Quality Education
Supervisor projects
- Towards Compatible Watermarking Schemes for Intellectual Property Protection in Modern Large Language Model Systems
- 2 Sep 2026
- Output Privacy in Lightweight MPC-based Secure Inference
- 17 Jul 2026
- From XONN to Transformer by Expanding BNN
- 25 Feb 2026
- Privacy Preserving LLM-based Recommender Systems
- 15 Aug 2025
- Practical Defense Against Backdoor Attacks in Spiking Neural Networks
- 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
- Enhancing Privacy Protection for Machine Learning as a Service
- 8 Nov 2022
Teaching interests
My teaching covers undergraduate and postgraduate cybersecurity and computing. At RMIT University, my course coordination and lecturing roles have included:
- Security Testing (INTE2547/2580): Coordinator and Lecturer for undergraduate and postgraduate students, Semester 2, 2023–2025.
- IT Infrastructure and Security (COSC2737): Coordinator and Lecturer for postgraduate students, Semester 1, 2025.
- Programming Bootcamp 1 (COSC2801): Lead and Lecturer for postgraduate students, Semester 1, 2023–2024.
I was the sole recipient of the RMIT STEM College Learning and Teaching Award for Excellence – Early Career Educator in 2024. Security Testing received STEM College Top Five Course Awards in 2023 and 2024, and IT Infrastructure and Security received a STEM College Top High Volume Courses Award in 2025.
My earlier teaching contributions include Cloud Security and Security in Computing and Information Technology at RMIT, and Software Security at Monash University. I have also contributed to RMIT’s Master of Cyber Security Program Design Team (2024) and ACS Accreditation Steering Committee (2023).
Research interests
I have been working on secure 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. My design philosophy is:
- Devising lightweight and fundamental secure computation protocols. I am particularly interested in the cryptographic techniques like secure multiparty computation, function secret sharing, zero knowledge proof.
- Unveiling and mitigating output privacy risks. Legitimate secure inference results can still be exploited by AI attacks to recover the AI model and its training data information, resulting in output privacy breach. I aim to set out the systematic investigation of such an exploitation and enable mitigation techniques to remedy the risks, like guarding membership privacy (SIGuard, Sige).
- 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), deep graph learning (OblivGNN, OblivDGL), secure outsourced computation in the cloud (Sonic), mobile-edge computing (Leia).
Beyond secure computation, I am also interested in AI and machine learning privacy and security. I also explore the intersections of these topics with secure computation.
