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6 篇
平均评分
年均产出3.0 篇/年
Yinzhi Cao
研究方向
Adversarial Machine Learning · Web Security · System Security · Federated Learning Privacy
20
A Robust Certified Machine Unlearning Method Under Distribution Shift
ICLR 2026Rejected
二作23
Computer-Use Agent Frameworks Can Expose Realistic Risks Through Tactics, Techniques, and Procedures
ICLR 2026Rejected
5
CoLa: A Choice Leakage Attack Framework To Expose Privacy Risks In Subset Training
ICLR 2026Withdrawn
三作6
AdaProb: Towards Efficient Machine Unlearning via Adaptive Probability
ICLR 2026Withdrawn
通讯6
Mirror Mirror on the Wall, Have I Forgotten it All? A New Framework for Evaluating Machine Unlearning
ICLR 2026Rejected