A privacy-preserving federated learning scheme with homomorphic encryption and edge computing

With the rapid advancement of data-driven technologies, safeguarding data privacy has become a focal concern in both academia and industry. Traditional data processing methods typically rely on centralized storage and computation, which increases vulnerability to privacy breaches, particularly during data transmission and storage. To address these challenges, we propose a privacy-preserving federated learning framework integrating homomorphic encryption with an added trust chain. The trust chain enables transparent, immutable recording of data processing stages, significantly enhancing system reliability and trustworthiness. Participants employ homomorphic encryption to ensure that data remains encrypted…