影响力指数

-/100

发表论文2 篇

平均评分3.8

年均产出2.0 篇/年

Tong Qiao

Associate Professor@Hangzhou Dianzi University·中国·OpenReview

研究方向

AI security · Multimedia forensics

BadReward: Clean-Label Poisoning of Reward Models in Text-to-Image RLHF

ICLR 2026Withdrawn

Black-Box Guardrail Reverse-engineering Attack

ICLR 2026Withdrawn

合作者 (9)