影响力指数

-/100

发表论文3 篇

平均评分3.7

年均产出1.5 篇/年

Yuan Xun

PhD student@University of the Chinese Academy of Sciences·中国·OpenReview

研究方向

adversarial attack and defense · deep learning · computer vision

PersGuard: Preventing Malicious Personalization in Text-to-Image Diffusion via Model Backdoors

ICLR 2026Withdrawn

RobustIT: Adapter-Centric and Attack-Agnostic Anti-Backdoor Instruction Tuning

ICLR 2026Withdrawn

CleanerCLIP: Fine-grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning

ICLR 2025Withdrawn

合作者 (5)

博士导师3 篇