影响力指数

-/100

发表论文3 篇

平均评分4.4

年均产出1.5 篇/年

Yuelin Xu

PhD student@CISPA Helmholtz Center for Information Security·德国·OpenReview

研究方向

Adversarial Machine Learning

How Learning Dynamics Drive Adversarially Robust Generalization?

ICLR 2026Rejected

GREAT: Generalizable Backdoor Attacks in RLHF via Emotion-Aware Trigger Synthesis

ICLR 2026Withdrawn

Understanding Adversarially Robust Generalization via Weight-Curvature Index

ICLR 2025Rejected

合作者 (3)

博士导师3 篇

Subrat Kishore Dutta