REA Press Null REA Press3042-31203042-3120 REA Press https://doi.org/10.22105/ahse.v3i2.65 Research Article Federated learning, Dementia diagnosis, Data poisoning attacks, Backdoor attacks, Robust aggregation Enhancing the Robustness of Federated Learning Models for Dementia Diagnosis Against Data Poisoning AttacksEnhancing the Robustness of Federated Learning Models for Dementia Diagnosis Against Data Poisoning Attacks Ebrahimzadeh Fatemeh Department of Computer Engineering, Ayandegan University, Tonekabon, Iran. Kaveh Sedigheh Department of Computer Engineering, Ayandegan University, Tonekabon, Iran. Falah Rad Mohsen Department of Computer Engineering, La.C., Islamic Azad University, Lahijan, Iran. 06 2026 27 06 2026 3 2 © 2026 REA Press 2026

This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

 Enhancing the Robustness of Federated Learning Models for Dementia Diagnosis Against Data Poisoning Attacks

Federated Learning (FL) enables privacy preserving dementia diagnosis but is vulnerable to poisoning attacks. We propose a hybrid defense integrating robust aggregation, client behavior analysis, feature consistency validation, and anomaly aware training. Results on ADNI, OASIS-3, and DementiaBank improve robustness while maintaining accuracy.

Null