Related papers: Efficient Homomorphically Encrypted Convolutional …

Privacy has gained a growing interest nowadays due to the increasing and unmanageable amount of produced confidential data. Concerns about the possibility of sharing data with third parties, to gain fruitful insights, beset enterprise…

One of the biggest concerns for many applications in cloud computing lies in data privacy. A potential solution to this problem is homomorphic encryption (HE), which supports certain operations directly over the ciphertexts. Conventional HE…

The growing body of literature on training-data reconstruction attacks raises significant concerns about deploying neural network classifiers trained on sensitive data. However, differentially private (DP) training (e.g. using DP-SGD) can…

We present RHODE, a novel system that enables privacy-preserving training of and prediction on Recurrent Neural Networks (RNNs) in a cross-silo federated learning setting by relying on multiparty homomorphic encryption. RHODE preserves the…

Federated learning (FL) with fully homomorphic encryption (FHE) effectively safeguards data privacy during model aggregation by encrypting local model updates before transmission, mitigating threats from untrusted servers or eavesdroppers…

Fully Homomorphic Encryption (FHE) is rapidly emerging as a promising foundation for privacy-preserving cloud services, enabling computation directly on encrypted data. As FHE implementations mature and begin moving toward practical…

In this work, we propose ENSEI, a secure inference (SI) framework based on the frequency-domain secure convolution (FDSC) protocol for the efficient execution of privacy-preserving visual recognition. Our observation is that, under the…

We present the first theoretical convergence analysis of machine learning training under fully homomorphic encryption (FHE), combined with a differentially private (DP) training algorithm tailored to encrypted computation. Our approach…

The mod function plays a critical role in numerous data encoding and cryptographic primitives. However, the widely used CKKS homomorphic encryption (HE) scheme supports only arithmetic operations, making it difficult to perform mod…

Federated Learning is a well-researched approach for collaboratively training machine learning models across decentralized data while preserving privacy. However, integrating Homomorphic Encryption to ensure data confidentiality introduces…

Translating or rotating an input image should not affect the results of many computer vision tasks. Convolutional neural networks (CNNs) are already translation equivariant: input image translations produce proportionate feature map…

In order to prevent leaking input information from intermediate-layer features, this paper proposes a method to revise the traditional neural network into the rotation-equivariant neural network (RENN). Compared to the traditional neural…

Federated Learning (FL) enables collaborative model training across distributed clients without sharing raw data, making it a promising approach for privacy-preserving machine learning in domains like Connected and Autonomous Vehicles…

Homomorphic Encryption (HE) is one of the most promising post-quantum cryptographic schemes that enable privacy-preserving computation on servers. However, noise accumulates as we perform operations on HE-encrypted data, restricting the…

This paper proposes a fully homomorphic encryption encapsulated difference expansion (FHEE-DE) scheme for reversible data hiding in encrypted domain (RDH-ED). In the proposed scheme, we use key-switching and bootstrapping techniques to…

Cloud computing is the broad and diverse phenomenon. Users are allowed to store huge amount of data on cloud storage for future use. Most of the cloud service providers store data in plain text format or in secured manner but client will…

Homomorphic encryption is a powerful cryptographic tool that enables secure computations on the private data. It evaluates any function for any operation securely on the encrypted data without knowing its corresponding plaintext. For…

Artificial intelligence (AI) increasingly powers sensitive applications in domains such as healthcare and finance, relying on both linear operations (e.g., matrix multiplications in large language models) and non-linear operations (e.g.,…

Privacy-preserving federated learning (PPFL) aims to train a global model for multiple clients while maintaining their data privacy. However, current PPFL protocols exhibit one or more of the following insufficiencies: considerable…

Federated learning (FL) enables distributed computation of machine learning models over various disparate, remote data sources, without requiring to transfer any individual data to a centralized location. This results in an improved…