Author

Ziming Hong

Observed name: Hong, Ziming

Institutions: The University of Sydney, University of Electronic Science and Technology of China

Observed institutions: The University of Sydney, University of Electronic Science and Technology of China

OpenAlex ID: A5125250786

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

2026 · Xiang, Yongli, Hong, Ziming, et al. · arXiv (Cornell University) · 12

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

2026 · Zheng, Bowen, Xiang, Yongli, et al. · arXiv (Cornell University) · 10

Is Gradient Ascent Really Necessary? Memorize to Forget for Machine Unlearning

2026 · Huang, Zhuo, Wang, Qizhou, et al. · arXiv (Cornell University) · 6

Delving into the Temporal Challenges of Unified Video Protection Against Image-to-Video and Fine-Tuning-based Customization

2026 · Huang, Yuxin, Hong, Ziming, et al. · arXiv (Cornell University) · 5

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

2026 · Zhao, Longjie, Hong, Ziming, et al. · arXiv (Cornell University) · 2

Adjustable Text-Guided Backdoor Attacks with Natural-Word Triggers on Multimodal Pretrained Models

2026 · Zhang, Yiyang, Yu, Chaojian, et al. · arXiv (Cornell University) · 1

Immunizing 3D Gaussian Generative Models Against Unauthorized Fine-Tuning via Attribute-Space Traps

2026 · Zhang, Jianwei, Cao, Sihan, et al. · arXiv (Cornell University) · 1

Storage Is Not Strategy: State-Conditioned Support Control for LLM Unlearning

2026 · Qian, Tianhao, Hong, Ziming, et al. · arXiv (Cornell University)

Works count: 8

Citation count: 37

H-index: 4

I10-index: 2