Oct 2026· Proceedings on Privacy Enhancing Technologies· Vol 2026, pp. 526-541· 1 citation
TL;DR
FHEON is presented, an open-source configurable framework for developing privacy-preserving neural network models for inference using the CKKS scheme of HE, and outperform all state-of-the-art HE inference works in both latency and memory utilization.
Abstract
The widespread adoption of Machine Learning as a Service raises critical privacy and security concerns, particularly about data confidentiality and trust in both cloud providers and the machine learning models provided. Homomorphic Encryption (HE) has emerged as a promising solution to these problems, allowing computations on encrypted data without decryption. Despite its potential, existing works that integrate HE into neural networks are often limited to specific architectures or classes. This leaves a wide gap in providing a framework for easy development of HE-friendly privacy-preserving neural network models similar to what we have in the broader field of machine learning. In this paper, we present FHEON, an open-source configurable framework for developing privacy-preserving neural network models for inference using the CKKS scheme of HE. FHEON introduces optimized and configurable implementations of privacy-preserving neural network layers, including convolution layers, average pooling layers, ReLU activation functions, and fully connected layers. These layers are configured using standard parameters such as input channels, output channels, kernel size, stride, and padding to support arbitrary convolution neural network (CNN) architectures. Furthermore, FHEON provides utility functions that ease usage and adoption. We assess the performance of FHEON using several CNN architectures, including LeNet-5, VGG-11, VGG-16, ResNet-20, and ResNet-34. FHEON maintains encrypted-domain accuracies within +-1% of their plaintext counterparts for ResNet-20 and LeNet-5 models. Notably, on a consumer-grade CPU, the models built on FHEON achieved 98.5% accuracy with a latency of 13 seconds on MNIST using LeNet-5, and 92.2% accuracy with a latency of 403 seconds on CIFAR-10 using ResNet-20. Though configurable, FHEON outperform all state-of the-art HE inference works in both latency and memory utilization. Additionally, FHEON operates within a practical memory budget requiring not more than 42.3 GB for VGG-16.
Deep learning is becoming popular in cloud applications and serves to provide intelligent services; data aggregation in a central location makes sensitive information vulnerable to privacy breaches, regulatory infractions, and adversarial manipulation. All modern privacy mechanisms offer partial protection and frequently lack accuracy, scalability, or practicality in their operations. To overcome these limitations, a federated deep learning model is formulated so that secure joint learning can occur without transferring raw data across the domains of ownership. The framework incorporates training that is decentralized, training that uses differential privacy, training that uses secure aggregation, training that uses encrypted communication, and training that uses trust-based anomaly defense to defend against leakage, poisoning, and inference attacks. It also supports heterogeneous and highly non-IID datasets using adaptive coordination and stability-relevant participation regulation and meets emerging data protection requirements. The methods of resource-conscious orchestration and the optimization of communication eliminate overhead without obstructing the effectiveness of learning. The paradigm has therefore formed a privacy-by-design intelligent cloud ecosystem which ensures confidentiality, maintains performance, enhances robustness, and ensures responsible AI implementation in privacy-related sectors of healthcare, finance, governance, and smart infrastructure.
Sribidhya Mohanty, Pallavi Gupta, Anil Pratap Singh et al.· 2026 International Conferenc...· 0 citations
The rapid growth of machine learning (ML) technologies has raised concerns about the privacy and security of sensitive data used in training models. Privacy-preserving techniques such as federated learning, homomorphic encryption, and differential privacy are emerging solutions to protect data in ML applications. However, these techniques often face challenges in terms of scalability, performance, and compliance with data privacy regulations. Sovereign Cloud environments, characterized by strict data governance and jurisdictional controls, offer a potential solution for addressing these challenges. This paper presents a novel framework for integrating privacy-preserving ML techniques within Sovereign Cloud infrastructures. By combining cutting-edge cryptographic approaches with the data sovereignty features of Sovereign Clouds, our framework ensures data privacy, legal compliance, and efficient machine learning at scale. We discuss key challenges in data privacy, scalability, and legal compliance, and propose a set of best practices for deploying privacy-preserving ML in these environments. Additionally, we evaluate the proposed framework through case studies, demonstrating its potential in sectors such as healthcare and finance. The results show that our framework provides a balanced approach to privacy, scalability, and performance, contributing to the future of secure and responsible ML deployment.
Ahmed Hassan· International Journal of Dat...· 0 citations
This study explores the integration of homomorphic encryption and differential privacy techniques to enhance data privacy and security in Federated Learning (FL) systems. FL allows data to remain on local devices, eliminating the need for centralized data collection; however, sensitive information may still be leaked during model updates. To address this issue, homomorphic encryption enables computations on encrypted data, while differential privacy prevents the extraction of individual information through statistical techniques applied to model outputs. The proposed architecture was tested on the Framingham, Pima Indians Diabetes, and Bank Marketing datasets, revealing that enhanced privacy can be achieved without significantly compromising model accuracy. Furthermore, the impact of data heterogeneity among clients on model performance was analyzed, and it was concluded that strategies such as the careful selection of differential privacy parameters and training settings, along with the use of larger datasets, can improve the efficiency of FL. The findings demonstrate that privacy-preserving and high-performance artificial intelligence systems can be securely applied in sensitive domains such as healthcare and finance.
Cagdas Karatas, Hibanur Karadogan, A. Ertug et al.· 0 citations
The SecureCROWN framework is built upon secure two-party computation (2PC), and enables a model owner and a data owner to jointly compute certified robustness bounds -- revealing only the final result while provably protecting both parties' private data under the semi-honest security model.
Nianyun Song, Xiaokun Luan, Yu Guo et al.· 1 citation