6 papers
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…
A theoretical model for task routing in mixture-of-expert transformers
Vinoth Nandakumar, Yongli Xiang, Yunzhi Yao +2
Mixture-of-experts (MoE) layers enable the scaling of transformer models while keeping the inference compute fixed. While task-expert specialization has been observed in empirical…
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…
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…