Related papers: EFFACT: A Highly Efficient Full-Stack FHE Accelera…

Computational privacy is a property of cryptographic system that ensures the privacy of data being processed at an untrusted server. Fully Homomorphic Encryption Schemes (FHE) promise to provide such property. Contemporary FHE schemes are…

Face recognition is central to many authentication, security, and personalized applications. Yet, it suffers from significant privacy risks, particularly arising from unauthorized access to sensitive biometric data. This paper introduces…

Homomorphic encryption enables arbitrary computation over data while it remains encrypted. This privacy-preserving feature is attractive for machine learning, but requires significant computational time due to the large overhead of the…

Addressing the challenge of balancing security and efficiency when deploying machine learning systems in untrusted environments, such as federated learning, remains a critical concern. A promising strategy to tackle this issue involves…

Accelerating Human Action Recognition (HAR) efficiently for real-time surveillance and robotic systems on edge chips remains a challenging research field, given its high computational and memory requirements. This paper proposed an…

Traditional Fully Homomorphic Encryption (FHE) schemes often suffer from prohibitive computational overhead and complex noise management. In this paper, we propose a novel symmetric FHE through a mechanism of plaintext fragmentation and…

Homomorphic encryption (HE) enables computations directly on encrypted data, offering strong cryptographic guarantees for secure and privacy-preserving data storage and query execution. However, despite its theoretical power, practical…

Fully Homomorphic Encryption (FHE) enables secure computation over encrypted data, but its computational cost remains a major obstacle to practical deployment. To mitigate this overhead, many studies have explored GPU acceleration for the…

Graph Neural Networks (GNNs) have achieved state-of-the-art performance in various graph-based learning tasks. However, enabling privacy-preserving GNNs in encrypted domains, such as under Fully Homomorphic Encryption (FHE), typically…

Fully homomorphic encryption (FHE) is a promising cryptographic primitive for realizing private neural network inference (PI) services by allowing a client to fully offload the inference task to a cloud server while keeping the client data…

With the rapid advancements in machine learning, models have become increasingly capable of learning and making predictions in various industries. However, deploying these models in critical infrastructures presents a major challenge, as…

Privacy-preserving neural network (NN) inference can be achieved by utilizing homomorphic encryption (HE), which allows computations to be directly carried out over ciphertexts. Popular HE schemes are built over large polynomial rings. To…

In contemporary cloud-based services, protecting users' sensitive data and ensuring the confidentiality of the server's model are critical. Fully homomorphic encryption (FHE) enables inference directly on encrypted inputs, but its…

Federated Learning (FL) is susceptible to privacy attacks, such as data reconstruction attacks, in which a semi-honest server or a malicious client infers information about other clients' datasets from their model updates or gradients. To…

New cryptographic techniques such as homomorphic encryption (HE) allow computations to be outsourced to and evaluated blindfolded in a resourceful cloud. These computations often require private data owned by multiple participants, engaging…

The deployment of deep neural networks (DNNs) in privacy-sensitive environments is constrained by computational overheads in fully homomorphic encryption (FHE). This paper explores unstructured sparsity in FHE matrix multiplication schemes…

We propose a framework for compile-time ciphertext synthesis in fully homomorphic encryption (FHE) systems, where ciphertexts are constructed from precomputed encrypted basis vectors combined with a runtime-scaled encryption of zero. This…

Recent work using Fully Homomorphic Encryption (FHE) has made non-interactive privacy-preserving inference of deep Convolutional Neural Networks (CNN) possible. However, the performance of these methods remain limited by their heavy…

Fully Homomorphic Encryption over the torus (TFHE) enables computation on encrypted data without decryption, making it a cornerstone of secure and confidential computing. Despite its potential in privacy preserving machine learning, secure…

Plaintext-ciphertext matrix multiplication (PC-MM) is an indispensable tool in privacy-preserving computations such as secure machine learning and encrypted signal processing. While there are many established algorithms for…