影响力指数

-/100

发表论文4 篇

平均评分4.3

年均产出1.3 篇/年

Hai Huang

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

研究方向

Backdoor Attacks · Privacy Risks in Machine Learning · Poisoning Attacks

Sparse Models, Sparse Safety: Unsafe Routes in Mixture-of-Experts LLMs

ICLR 2026Rejected

ACE: Attack Combo Enhancement Against Machine Learning Models

ICLR 2025Withdrawn

合作者 (10)

博士导师4 篇

博士导师4 篇

Emiliano De Cristofaro