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
-/100
发表论文3 篇
平均评分
年均产出3.0 篇/年
Bin Ma
研究方向
Trustworthy AI · Graph Neural Networks
30
Poisoning the Inner Prediction Logic of Graph Neural Networks for Clean-Label Backdoor Attacks
ICLR 2026Rejected
二作16
Protap: A Benchmark for Protein Modeling on Realistic Downstream Applications
ICLR 2026Rejected
三作20
How Explanations Leak the Decision Logic: Stealing Graph Neural Networks via Explanation Alignment
ICLR 2026Rejected
一作