18 papers
Understanding Trajectory Heterogeneity in Federated World Model Learning
Yipan Wei, Zhaokun Yan, Ziming Hong +2
World models learn state evolution from trajectories, making access to temporal context a central training requirement. Federated learning can use distributed records, while owners…
On Unlearning for Time-series Forecasting
Zeyu Shi, Yanhui Luo, Ziming Hong +4
Time-series forecasting is widely used in sensitive domains. Models in these settings are often trained on longitudinal user- or entity-level records, which may later require remov…
Storage Is Not Strategy: State-Conditioned Support Control for LLM Unlearning
Tianhao Qian, Ziming Hong, Chongyang Gao +2
Many localized large language model (LLM) unlearning methods select a small parameter subset from a localization signal and keep it fixed during optimization. The parameters most a…
When Agents Learn to Be You: Benchmarking Privacy Leakage, Impersonation Risk, and Defenses in Persona Skills
Yongli Xiang, Zhifang Zhang, Bojun Yang +4
Persona skills distill personal interaction histories into portable and executable artifacts for downstream agents. While enabling flexible personalization, this process concentrat…
Delving into the Temporal Challenges of Unified Video Protection Against Image-to-Video and Fine-Tuning-based Customization
Yuxin Huang, Ziming Hong, Mingming Gong +3
Recent diffusion-based video generation models have enabled high-quality personalized video customization through both tuning-based pipelines, which fine-tune a video diffusion mod…
Immunizing 3D Gaussian Generative Models Against Unauthorized Fine-Tuning via Attribute-Space Traps
Jianwei Zhang, Sihan Cao, Chaoning Zhang +7
Recent large-scale generative models enable high-quality 3D synthesis. However, the public accessibility of pre-trained weights introduces a critical vulnerability. Adversaries can…
Adjustable Text-Guided Backdoor Attacks with Natural-Word Triggers on Multimodal Pretrained Models
Yiyang Zhang, Chaojian Yu, Ziming Hong +4
This paper presents Text-Guided Backdoor (TGB), an adjustable backdoor attack against multimodal pretrained models that uses natural-word triggers, namely words that can naturally…
When Safety Collides: Resolving Multi-Category Harmful Conflicts in Text-to-Image Diffusion via Adaptive Safety Guidance
Yongli Xiang, Ziming Hong, Zhaoqing Wang +3
Text-to-Image (T2I) diffusion models have demonstrated significant advancements in generating high-quality images, while raising potential safety concerns regarding harmful content…
VII: Visual Instruction Injection for Jailbreaking Image-to-Video Generation Models
Bowen Zheng, Yongli Xiang, Ziming Hong +4
Image-to-Video (I2V) generation models, which condition video generation on reference images, have shown emerging visual instruction-following capability, allowing certain visual c…
Is Gradient Ascent Really Necessary? Memorize to Forget for Machine Unlearning
Zhuo Huang, Qizhou Wang, Ziming Hong +3
For ethical and safe AI, machine unlearning rises as a critical topic aiming to protect sensitive, private, and copyrighted knowledge from misuse. To achieve this goal, it is commo…
Intellectual Property Protection for 3D Gaussian Splatting Assets: A Survey
Longjie Zhao, Ziming Hong, Jiaxin Huang +3
3D Gaussian Splatting (3DGS) has become a mainstream representation for real-time 3D scene synthesis, enabling applications in virtual and augmented reality, robotics, and 3D conte…
AdLift: Lifting Adversarial Perturbations to Safeguard 3D Gaussian Splatting Assets Against Instruction-Driven Editing
Ziming Hong, Tianyu Huang, Runnan Chen +4
Recent studies have extended diffusion-based instruction-driven 2D image editing pipelines to 3D Gaussian Splatting (3DGS), enabling faithful manipulation of 3DGS assets and greatl…
RDSplat: Robust Watermarking for 3D Gaussian Splatting Against 2D and 3D Diffusion Editing
Longjie Zhao, Ziming Hong, Zhenyang Ren +3
3D Gaussian Splatting (3DGS) has become a leading representation for high-fidelity 3D assets, yet protecting these assets via digital watermarking remains an open challenge. Existi…
Prototype-Guided Curriculum Learning for Zero-Shot Learning
Lei Wang, Shiming Chen, Guo-Sen Xie +4
In Zero-Shot Learning (ZSL), embedding-based methods enable knowledge transfer from seen to unseen classes by learning a visual-semantic mapping from seen-class images to class-lev…
When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Need
Ziming Hong, Runnan Chen, Zengmao Wang +3
Data-free knowledge distillation (DFKD) transfers knowledge from a teacher to a student without access the real in-distribution (ID) data. Its common solution is to use a generator…
Jailbreaking the Non-Transferable Barrier via Test-Time Data Disguising
Yongli Xiang, Ziming Hong, Lina Yao +2
Non-transferable learning (NTL) has been proposed to protect model intellectual property (IP) by creating a "non-transferable barrier" to restrict generalization from authorized to…
Toward Robust Non-Transferable Learning: A Survey and Benchmark
Ziming Hong, Yongli Xiang, Tongliang Liu
Over the past decades, researchers have primarily focused on improving the generalization abilities of models, with limited attention given to regulating such generalization. Howev…
Visual-Augmented Dynamic Semantic Prototype for Generative Zero-Shot Learning
Wenjin Hou, Shiming Chen, Shuhuang Chen +6
Generative Zero-shot learning (ZSL) learns a generator to synthesize visual samples for unseen classes, which is an effective way to advance ZSL. However, existing generative metho…