Skoči na glavni sadržaj

Izvorni znanstveni članak

https://doi.org/10.32985/ijeces.15.5.4

Federated Learning Implementation with Privacy Leakage Prevention for Hand-Written Digit Recognition

N. Indira Priyadarsini ; Department of Computer Science Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, AP, India *
Raja Govindan ; Department of Computer Science Engineering, Koneru Lakshmaiah Education Foundation Vaddeswaram, AP, India

* Dopisni autor.


Puni tekst: engleski pdf 1.533 Kb

str. 415-425

preuzimanja: 126

citiraj


Sažetak

Federated learning (FL) has brought significant advantages to applications where collaborative learning should occur at multiple participating devices to enhance user experience in specific tasks. However, FL results in privacy leakage when n-1 clients collude to infer the model of another client. In this paper, we not only implement an FL framework but propose a methodology for preventing privacy leakage while realizing machine learning-based automatic hand-written digit recognition. Our framework supports the FL of deep networks where models trained locally are averaged. Two machine learning models Convolutional Neural Network (CNN) and Multilayer Perceptron (MLP) are implemented with FL. We proposed an algorithm, Federated Averaging with Privacy Leakage Prevention (FA-PLP), for model averaging to be done by the server. Our algorithm exploits differential privacy (DP) for realizing model averaging while getting rid of chances of privacy leakage. We evaluated our framework with two distributions of the MNIST dataset. Our empirical results revealed that FA-PLP with the CNN model could achieve the highest accuracy of 95.38%.

Ključne riječi

Federated Learning; Machine Learning; Deep Learning; Privacy; Collaborative Machine Learning;

Hrčak ID:

316784

URI

https://hrcak.srce.hr/316784

Datum izdavanja:

13.5.2024.

Posjeta: 381 *