影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
36.69/100
前 17.1%
全站排名 #11,021
发表论文7 篇
平均评分
年均产出3.5 篇/年
Chia-Mu Yu
研究方向
Jailbreak · Text-to-Image Model Security · Backdoor
29
Safety Depth in Large Language Models: A Markov Chain Perspective
NeurIPS 2025Poster
二作28
Information-Theoretical Principled Trade-off between Jailbreakability and Stealthiness on Vision Language Models
ICLR 2025Rejected
二作4
Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models
ICLR 2025Withdrawn
通讯24
Safe LoRA: The Silver Lining of Reducing Safety Risks when Finetuning Large Language Models
NeurIPS 2024Poster
22
Ring-A-Bell! How Reliable are Concept Removal Methods For Diffusion Models?
ICLR 2024Poster
23
Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective
ICLR 2024Poster
三作3
DPAF: Image Synthesis via Differentially Private Aggregation in Forward Phase
ICLR 2024Withdrawn
三作