I joined UNSW Sydney as a Postdoctoral Research Fellow in March 2026, where I am supervised by Prof. Yulei Sui. My research focuses on Machine Learning (ML), Federated Learning (FL), and AI Safety Testing, with a particular interest in trustworthy and secure AI systems.
I earned my Ph.D. from The University of Queensland, where my supervisors were A/Prof. Guangdong Bai and Prof. Helen Huang. My doctoral studies were supported by the CSIRO Data61 PhD Scholarship and Top-up Scholarship. At CSIRO Data61, my supervisors were Dr. Pathum Chamikara Mahawaga Arachchige and Dr. Mohan Baruwal Chhetri. I also received my Master’s degree in Data Science from UQ in 2022.
🔥 News
- 2026.01: 🎉🎉 Our paper on RL-guided reconstruction attack against machine unlearning is accepted by ICLR’26!
- 2026.01: 🎉🎉 Our paper on backdoor attack mitigation is accepted by WWW’26!
- 2025.12: 🎉🎉 Our paper on client-side detection against poisoning attacks is accepted by AsiaCCS’26!
- 2025.03: 🎉🎉 Two papers on vulnerability disclosure on T2I models and vunerability exploration in CFL are accepted by Oakland’25!
- 2024.12: 🎉🎉 I am invited to be an AE reviewer of USENIX Security’25!
- 2024.12: 🎉🎉 I am invited to be a reviewer of IEEE TDSC, TIFS, TSC, and Neural Network!
- 2024.10: 🎉🎉 I am invited to be a reviewer of PAKDD’25!
- 2024.08: 🎉🎉 Our paper on privacy leakage of language models is accepted by CCS’24!
- 2024.07: 🎉🎉 I am invited to be a reviewer of ACM CIKM’24!
- 2024.07: 🎉🎉 Our paper on unveiling IP vulnerabilities of GAN-based distributed ML is accepted by CIKM’24!
- 2023.08: 🎉🎉 Our paper on formalizing neural network perturbation is accepted by ICFEM’23!
- 2023.06: 🎉🎉 I am invited to be an AE reviewer of NDSS’24!
- 2023.06: 🎉🎉 I pass my first-year progress review confirmation!
- 2023.05: 🎉🎉 Our paper on mitigating membership inference threats in FL is accepted by AsiaCCS’23!
- 2022.04: 🎉🎉 I become a Ph.D. student at the University of Queensland!
📝 Selected Publications
ReTrace: Reinforcement Learning-Guided Reconstruction Attacks on Machine Unlearning
Mengyao Ma, Shuofeng Liu, Minhui Xue, Surya Nepal, Guangdong Bai. The Fourteenth International Conference on Learning Representations (ICLR), 2026.
Mengyao Ma, Shuofeng Liu, Viet Vo, Minghong Fang, Surya Nepal, Guangdong Bai. ACM ASIA Conference on Computer and Communications Security (AsiaCCS), Jun. 2026.
Modifier Unlocked: Jailbreaking Text-to-Image Models Through Prompts
Shuofeng Liu, Mengyao Ma, Minhui Xue, Guangdong Bai. IEEE Symposium on Security and Privacy (Oakland), Apr. 2025.
Practical Poisoning Attacks with Limited Byzantine Clients in Clustered Federated Learning
Viet Vo, Mengyao Ma, Guangdong Bai, Ryan Ko, Surya Nepal. IEEE Symposium on Security and Privacy (Oakland), Apr. 2025.
Mengyao Ma, Shuofeng Liu, Mahawaga Arachchige Pathum Chamikara, Mohan Baruwal Chhetri, Guangdong Bai. ACM International Conference on Information and Knowledge Management (CIKM), Jul. 2024.
Uncovering Gradient Inversion Risks in Practical Language Model Training
Xinguo Feng, Zhongkui Ma, Zihan Wang, Chegne Eu Joe, Mengyao Ma, Alsharif Abuadbba, Guangdong Bai. ACM Computer and Communications Security Conference (CCS), Aug. 2024.
Mengyao Ma, Yanjun Zhang, Pathum Chamikara Mahawaga Arachchige, Leo Yu Zhang, Mohan Baruwal Chhetri, Guangdong Bai. ACM ASIA Conference on Computer and Communications Security (AsiaCCS), Apr. 2023.
Formalizing Robustness Against Character-Level Perturbations for Neural Network Language Models
Zhongkui Ma, Xinguo Feng, Zihan Wang, Shuofeng Liu, Mengyao Ma, Hao Guan, Mark Huasong Meng. International Conference on Formal Engineering Methods (ICFEM), Aug. 2023.
🎖 Awards
- 2024.09: 🏆 SIGIR Travel Grant for presenting at CIKM’24, Boise, USA.
- 2022.01: 🎓 CSIRO’s Data61 Full Scholarship with top-up funding.
- 2021.11: 🏅 Dean’s Commendation for Academic Excellence at UQ.
📌 Service
- Web Chair: IWQoS 2025.
- Leader of Local Committee: ICFEM 2023.
- AE Reviewer: USENIX Security 2025, NDSS 2024.
- Reviewer: PAKDD 2025, IEEE TDSC, TSC, TIFS, Neural Networks.