Enhancing Noisy Functional Encryption for Privacy-Preserving Machine Learning

2025/05/09 by Linda Scheu-Hachtel, Scheu-Hachtel, Linda, Jasmin Zalonis +1
Computer Science · #Advanced Authentication Protocols Security #Cryptography and Data Security #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Privacy-Preserving Technologies in Data

paper · pdf · doi:10.48550/arxiv.2505.05843

openalex publication_date 2025/05/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Functional encryption (FE) has recently attracted interest in privacy-preserving machine learning (PPML) for its unique ability to compute specific functions on encrypted data. A related line of work focuses on noisy FE, which ensures differential privacy in the output while keeping the data encrypted. We extend the notion of noisy multi-input functional encryption (NMIFE) to (dynamic) noisy multi-client functional encryption ((Dy)NMCFE), which allows for more flexibility in the number of data holders and analyses, while protecting the privacy of the data holder with fine-grained access through the usage of labels. Following our new definition of DyNMCFE, we present DyNo, a concrete inner-product DyNMCFE scheme. Our scheme captures all the functionalities previously introduced in noisy FE schemes, while being significantly more efficient in terms of space and runtime and fulfilling a stronger security notion by allowing the corruption of clients. To further prove the applicability of DyNMCFE, we present a protocol for PPML based on DyNo. According to this protocol, we train a privacy-preserving logistic regression.

Citations

• FATE-LLM: A Industrial Grade Federated Learning Framework for Large Language Models
• Verifiable Fully Homomorphic Encryption
• Heal the Privacy: Functional Encryption and Privacy-Preserving Analytics
• Dynamic Differential-Privacy Preserving SGD
• Federated Learning: Challenges, Methods, and Future Directions
• Partially Encrypted Machine Learning using Functional Encryption
• CryptoNN: Training Neural Networks over Encrypted Data
• Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising
• Membership Inference Attacks against Machine Learning Models

Related

• Partially Encrypted Machine Learning using Functional Encryption
• Revisiting Secure Computation Using Functional Encryption: Opportunities and Research Directions
• Hawk: Accurate and Fast Privacy-Preserving Machine Learning Using Secure Lookup Table Computation
• Morse-STF: Improved Protocols for Privacy-Preserving Machine Learning
• Robust Representation Learning for Privacy-Preserving Machine Learning: A Multi-Objective Autoencoder Approach