Can We Trust the Similarity Measurement in Federated Learning?

no code implementations • 20 Oct 2023 • Zhilin Wang, Qin Hu, Xukai Zou

We first uncover the deficiencies of similarity metrics that high-dimensional local models, including benign and poisoned models, may be evaluated to have the same similarity while being significantly different in the parameter values.

Federated Learning Model Poisoning

Usability and Security of Different Authentication Methods for an Electronic Health Records System

no code implementations • 23 Feb 2021 • Saptarshi Purkayastha, Shreya Goyal, Bolu Oluwalade, Tyler Phillips, Huanmei Wu, Xukai Zou

From the PLS-SEM analysis, it was found that security has a positive impact on usability for Single sign-on and bio-capsule facial authentication methods.

Cryptography and Security