2 papers
cs.LG2025
FedMIA: An Effective Membership Inference Attack Exploiting "All for One" Principle in Federated Learning
Gongxi Zhu, Donghao Li, Hanlin Gu +3
Federated Learning (FL) is a promising approach for training machine learning models on decentralized data while preserving privacy. However, privacy risks, particularly Membership…
cs.LG2025
Noise May Contain Transferable Knowledge: Understanding Semi-supervised Heterogeneous Domain Adaptation from an Empirical Perspective
Yuan Yao, Xiaopu Zhang, Yu Zhang +2
Semi-supervised heterogeneous domain adaptation (SHDA) addresses learning across domains with distinct feature representations and distributions, where source samples are labeled w…