Advancing Practical Homomorphic Encryption for Federated Learning: Theoretical Guarantees and Efficiency Optimizations
By: Ren-Yi Huang , Dumindu Samaraweera , Prashant Shekhar and more
Potential Business Impact:
Protects private data when computers learn together.
Federated Learning (FL) enables collaborative model training while preserving data privacy by keeping raw data locally stored on client devices, preventing access from other clients or the central server. However, recent studies reveal that sharing model gradients creates vulnerability to Model Inversion Attacks, particularly Deep Leakage from Gradients (DLG), which reconstructs private training data from shared gradients. While Homomorphic Encryption has been proposed as a promising defense mechanism to protect gradient privacy, fully encrypting all model gradients incurs high computational overhead. Selective encryption approaches aim to balance privacy protection with computational efficiency by encrypting only specific gradient components. However, the existing literature largely overlooks a theoretical exploration of the spectral behavior of encrypted versus unencrypted parameters, relying instead primarily on empirical evaluations. To address this gap, this paper presents a framework for theoretical analysis of the underlying principles of selective encryption as a defense against model inversion attacks. We then provide a comprehensive empirical study that identifies and quantifies the critical factors, such as model complexity, encryption ratios, and exposed gradients, that influence defense effectiveness. Our theoretical framework clarifies the relationship between gradient selection and privacy preservation, while our experimental evaluation demonstrates how these factors shape the robustness of defenses against model inversion attacks. Collectively, these contributions advance the understanding of selective encryption mechanisms and offer principled guidance for designing efficient, scalable, privacy-preserving federated learning systems.
Similar Papers
Improving Efficiency in Federated Learning with Optimized Homomorphic Encryption
Cryptography and Security
Makes private AI training much faster.
SelectiveShield: Lightweight Hybrid Defense Against Gradient Leakage in Federated Learning
Distributed, Parallel, and Cluster Computing
Protects private info while training AI models.
Secure Distributed Learning for CAVs: Defending Against Gradient Leakage with Leveled Homomorphic Encryption
Cryptography and Security
Keeps car data private while learning.