Ziming's Homepage

Ziming Hong

Ph.D. Student

Sydney AI Centre

School of Computer Science

The University of Sydney

Address: J12/1 Cleveland St, Darlington, NSW 2008, Australia

Email: hoongzm@gmail.com; ziming.hong@sydney.edu.au

[Google Scholar]

Short Bio

I am currently a third-year Ph.D. candidate in the School of Computer Science at The University of Sydney, supervised by Prof. Tongliang Liu. I obtained my master's degree from the School of Electronic Information and Communications, Huazhong University of Science and Technology and my bachelor's degree from the School of Information Engineering, Wuhan University of Technology.

My research focuses on Trustworthy AI, with a particular emphasis on Intellectual Property (IP) protection:

👉 Data-centric IP protection: (1) Survey for 3DGS IP protection [Preprint]; (2) Protecting 3D Gaussian Splatting assets against diffusion-based editing [ICML 2026 (Spotlight)]; (3) Unlearnable videos against diffusion-based customization [Preprint].

👉 IP protection for AI models via non-transferable learning (NTL): (1) Benchmark for NTL [IJCAI 2025 (Survey Track)]; (2) NTL vs data-free knowledge distillation [ICML 2025]; (3) Black-box robustness of NTL models [CVPR 2025]; (4) White-box robustness analysis of NTL [CVPR 2024 (Highlight)]; (5) Causal-inspired NTL method [ICLR 2024 (Spotlight)].

👉 Generative model safety: (1) Harmful conflicts in Text-to-Image generation [CVPR 2026]; (2) Jailbreaking Image-to-Video generation via visual instruction [Preprint].

Selected Publications

(*Equal contribution; †Corresponding author)

My Video Stays Mine: Temporally Consistent Universal Adversarial Perturbations against Video Customization.

Y. Huang, Z. Hong, M. Gong, W. Wang, J. Zhang, T. Liu.

arXiv Preprint 2026

Intellectual Property Protection for 3D Gaussian Splatting Assets: A Survey.

L. Zhao, Z. Hong, J. Huang, R. Chen, M. Gong, T. Liu†.

arXiv Preprint 2026

VII: Visual Instruction Injection for Jailbreaking Image-to-Video Generation Models.

B. Zheng, Y. Xiang, Z. Hong, Z. Lin, C. Yu, T. Liu, X. You.

arXiv Preprint 2026

AdLift: Lifting Adversarial Perturbations to Safeguard 3D Gaussian Splatting Assets Against Instruction-Driven Editing.

Z. Hong, T. Huang, R. Chen, S. Ye†, M. Gong, B. Han, T. Liu.

ICML 2026 (Spotlight)

CVPR 2026 Workshop on SPAR-3D (Best Paper Award)

When Safety Collides: Resolving Multi-Category Harmful Conflicts in Text-to-Image Diffusion via Adaptive Safety Guidance.

Y. Xiang, Z. Hong†, Z. Wang, X. Zhao, B. Han, T. Liu†.

CVPR 2026

When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Need.

Z. Hong, R. Chen, Z. Wang†, B. Han, B. Du, T. Liu†.

ICML 2025

Toward Robust Non-Transferable Learning: A Survey and Benchmark.

Z. Hong*, Y. Xiang*, T. Liu†.

IJCAI 2025 (Survey Track)

Jailbreaking the Non-Transferable Barrier via Test-Time Data Disguising.

Y. Xiang, Z. Hong†, L. Yao, D. Wang, T. Liu†.

CVPR 2025

Your Transferability Barrier is Fragile: Free-Lunch for Transferring the Non-Transferable Learning.

Z. Hong, L. Shen, T. Liu†.

CVPR 2024 (Highlight)

Improving Non-Transferable Representation Learning by Harnessing Content and Style.

Z. Hong, Z. Wang, L. Shen, Y. Yao, Z. Huang, S. Chen, C. Yang, M. Gong, T. Liu†.

ICLR 2024 (Spotlight)

Semantic Compression Embedding for Generative Zero-Shot Learning.

Z. Hong*, S. Chen*†, G. Xie, W. Yang, J. Zhao, Y. Shao, Q. Peng, X. You†.

IJCAI 2022

Academic Services

Organizing Committee

LifeGenIP: Life-Cycle Intellectual Property Governance of Visual Generative Models @ ECCV 2026

Conference Reviewer

ICLR, NeurIPS, ICML, CVPR, ICCV, ECCV, AAAI, IJCAI, ACM MM, UAI, ACML, PRCV

Journal Reviewer

IJCV, TIP, TNNLS, TCSVT, TMM, TKDD, TMLR, KBS, EAAI, PR, NN, ESWA, Neurocomputing

Teaching

Teaching Assistant: COMP5328 Advanced Machine Learning, Semester 2, 2025 (The University of Sydney).

Google Sites

Report abuse