Integrating Homomorphic Encryption and Synthetic Data in FL for Privacy and Learning Quality

Federated learning (FL) enables collaborative training of machine learning models without sharing sensitive client data, making it a cornerstone for privacy-critical applications. However, FL faces the dual challenge of ensuring learning quality and robust privacy protection while keeping resource consumption low, particularly when using computationally expensive techniques such as homomorphic encryption (HE). In this work, we enhance an FL process that preserves privacy using HE by integrating it with synthetic data generation and an interleaving strategy. Specifically, our solution, named Alternating Federated Learning (Alt-FL), consists of alternating between local training with authentic data (authentic rounds) and local training with synthetic data (synthetic rounds) and transferring the encrypted and plaintext model parameters on authentic and synthetic rounds (resp.). Our approach improves learning quality (e.g., model accuracy) through datasets enhanced with synthetic data, preserves client data privacy via HE, and keeps manageable encryption and decryption costs through our interleaving strategy. We evaluate our solution against data leakage attacks, such as the DLG attack, demonstrating robust privacy protection. Also, Alt-FL provides 13.4% higher model accuracy and decreases HE-related costs by up to 48% with respect to Selective HE.

Key Contributions

• Alt-FL: an interleaved FL strategy alternating between authentic-data rounds (with HE-encrypted parameter transfers) and synthetic-data rounds (with plaintext transfers) to balance privacy, accuracy, and computational cost
• Integration of synthetic data generation into HE-protected FL to improve dataset balance and model accuracy (+13.4% over Selective HE)
• Reduction of homomorphic encryption overhead by up to 48% via the interleaving strategy, evaluated against DLG gradient inversion attacks

🛡️ Threat Analysis

Details

Similar Papers