Penerapan Federated Learning dalam Keamanan Data Pengguna pada Aplikasi Mobile

In the digital era that is full of user data processing, security and privacy are crucial issues, especially in mobile applications. Federated Learning (FL) emerged as an innovative solution in maintaining data confidentiality because the model training process is carried out locally on the user's device without sending raw data to a central server. This study aims to examine the application of FL in improving user data security, evaluate its effectiveness, and analyze the challenges of its implementation in mobile environments. Through a literature study approach and simulated experiments, the results of the study show that FL is able to significantly reduce the risk of data leakage. However, limited device resources and sync issues are major challenges. This research provides important insights into FL's potential in building a more secure mobile app ecosystem.