Enhancing Privacy Protection on Android Devices through Federated Learning and Differential Privacy
MATRIX Academic International Online Journal Of Engineering And Technology · 2025
DOI: 10.21276/matrix.2025.8.1.4 ↗Kurz gefasst
Fachartikel in der Zeitschrift MATRIX Academic International Online Journal Of Engineering And Technology, 2025. Verfasst von Manish Verma und 1 weiteren Autor:innen.
Abstract (Originalsprache)
The rapid expansion of Android devices has brought about significantconvenience and connectivity improvements, but it has also escalated the risk ofdata breaches and unauthorized access to sensitive information. This researchpresents a thorough investigation into the sources of data leakage within theAndroid ecosystem, evaluates existing detection methodologies. Through theanalysis of real-world data breaches, critical vulnerabilities are identified forandroid devices.The study evaluates the effectiveness of current detection tools and theirlimitations, revealing that while static and dynamic analysis techniques arevaluable, they are often resource-intensive and prone to false positives. Toaddress these challenges, a novel hybrid model integrating Federated Learning(FL) and Differential Privacy (DP) is proposed. This DP+FL model ensuresdata remains on user devices and adds noise to local model updates to maintainprivacy.Experimental results demonstrate that the DP+FL model significantlyoutperforms traditional FL and DP methods, achieving an accuracy of 95%,precision of 94%, recall of 95%, and F1 score of 94%. These findings indicatethat the DP+FL model not only enhances privacy protection but also maintainshigh model performance.
Zitieren
APA
Verma, M., & Nand, P. (2025). Enhancing Privacy Protection on Android Devices through Federated Learning and Differential Privacy. MATRIX Academic International Online Journal Of Engineering And Technology. https://doi.org/10.21276/matrix.2025.8.1.4
Vancouver
Verma M, Nand P. Enhancing Privacy Protection on Android Devices through Federated Learning and Differential Privacy. MATRIX Academic International Online Journal Of Engineering And Technology. 2025. doi:10.21276/matrix.2025.8.1.4
BibTeX
@article{Verma2025,
author = {Verma, Manish and Nand, Parma},
title = {Enhancing Privacy Protection on Android Devices through Federated Learning and Differential Privacy},
journal = {MATRIX Academic International Online Journal Of Engineering And Technology},
year = {2025},
doi = {10.21276/matrix.2025.8.1.4}
}
EUVIMED