The Role of Federated Learning in Enhancing Data Privacy in Distributed Environments in Indonesia
Uloženo v:
| Název: | The Role of Federated Learning in Enhancing Data Privacy in Distributed Environments in Indonesia |
|---|---|
| Autoři: | Ajub Ajulian ZM, Enda Wista Sinuraya, Bambang Winardi |
| Zdroj: | The Eastasouth Journal of Information System and Computer Science. 3:64-76 |
| Informace o vydavateli: | PT. Sanskara Karya Internasional, 2025. |
| Rok vydání: | 2025 |
| Popis: | This study investigates the role of federated learning (FL) in enhancing data privacy within distributed environments in Indonesia. With the increasing reliance on digital technologies, data privacy has become a critical concern, particularly in decentralized systems. A quantitative research approach was employed, involving 130 respondents from various professional backgrounds engaged with distributed data systems. Data were collected using a structured questionnaire with a five-point Likert scale (1–5) and analyzed using SPSS version 25. Descriptive, correlation, and regression analyses revealed that federated learning significantly contributes to improving confidentiality, trust, and compliance in distributed environments. The results indicate that FL not only safeguards sensitive data but also enhances stakeholder confidence and supports adherence to regulatory standards, such as Indonesia’s UU PDP. The study provides empirical evidence supporting the adoption of federated learning as a privacy-preserving technology and offers practical insights for organizations and policymakers seeking secure and compliant digital ecosystems. |
| Druh dokumentu: | Article |
| ISSN: | 3025-566X 3026-6041 |
| DOI: | 10.58812/esiscs.v3i01.720 |
| Rights: | CC BY SA |
| Přístupové číslo: | edsair.doi...........c3b921038c6a63c5293eb9c02830be2e |
| Databáze: | OpenAIRE |
Nájsť tento článok vo Web of Science | Abstrakt: | This study investigates the role of federated learning (FL) in enhancing data privacy within distributed environments in Indonesia. With the increasing reliance on digital technologies, data privacy has become a critical concern, particularly in decentralized systems. A quantitative research approach was employed, involving 130 respondents from various professional backgrounds engaged with distributed data systems. Data were collected using a structured questionnaire with a five-point Likert scale (1–5) and analyzed using SPSS version 25. Descriptive, correlation, and regression analyses revealed that federated learning significantly contributes to improving confidentiality, trust, and compliance in distributed environments. The results indicate that FL not only safeguards sensitive data but also enhances stakeholder confidence and supports adherence to regulatory standards, such as Indonesia’s UU PDP. The study provides empirical evidence supporting the adoption of federated learning as a privacy-preserving technology and offers practical insights for organizations and policymakers seeking secure and compliant digital ecosystems. |
|---|---|
| ISSN: | 3025566X 30266041 |
| DOI: | 10.58812/esiscs.v3i01.720 |