Related papers: Inhibitor Transformers and Gated RNNs for Torus Ef…

Privacy-Preserving Neural Networks (PPNN) are advanced to perform inference without breaching user privacy, which can serve as an essential tool for medical diagnosis to simultaneously achieve big data utility and privacy protection. As one…

Federated Learning trains machine learning models on distributed devices by aggregating local model updates instead of local data. However, privacy concerns arise as the aggregated local models on the server may reveal sensitive personal…

Fully homomorphic encryption (FHE) is in the spotlight as a definitive solution for privacy, but the high computational overhead of FHE poses a challenge to its practical adoption. Although prior studies have attempted to design ASIC…

We address two fundamental challenges in adapting general deep CNNs for FHE-based inference: approximating non-linear activations such as ReLU with low-degree polynomials while minimizing accuracy degradation, and overcoming the ciphertext…

With the rapid increase in cloud computing, concerns surrounding data privacy, security, and confidentiality also have been increased significantly. Not only cloud providers are susceptible to internal and external hacks, but also in some…

In contrast to RNNs, which compress their history into a single hidden state, Transformers can attend to all past tokens directly. However, standard Transformers rely solely on the hidden state from the previous layer to represent the…

It is increasingly important to enable privacy-preserving inference for cloud services based on Transformers. Post-quantum cryptographic techniques, e.g., fully homomorphic encryption (FHE), and multi-party computation (MPC), are popular…

Homomorphic Encryption (HE) is an emerging encryption scheme that allows computations to be performed directly on encrypted messages. This property provides promising applications such as privacy-preserving deep learning and cloud…

In previous work, Boemer et al. introduced nGraph-HE, an extension to the Intel nGraph deep learning (DL) compiler, that enables data scientists to deploy models with popular frameworks such as TensorFlow and PyTorch with minimal code…

We apply quantum homomorphic encryption (QHE) schemes suitable for circuits with a polynomial number of $T/T^{\dagger}$-gates to Grover's algorithm, performing a simulation in Qiskit of a Grover circuit that contains 3 qubits. The…

In this paper, we present the demonstration of training a four-layer neural network entirely using fully homomorphic encryption (FHE), supporting both single-output and multi-output classification tasks in a non-interactive setting. A key…

Federated Learning (FL) enables collaborative training while keeping sensitive data on clients' devices, but local model updates can still leak private information. Hybrid Homomorphic Encryption (HHE) has recently been applied to FL to…

Homomorphic encryption (HE) has found extensive utilization in federated learning (FL) systems, capitalizing on its dual advantages: (i) ensuring the confidentiality of shared models contributed by participating entities, and (ii) enabling…

State-of-the-art Transformer-based models, with gigantic parameters, are difficult to be accommodated on resource constrained embedded devices. Moreover, with the development of technology, more and more embedded devices are available to…

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…

Time-series data in real-world settings typically exhibit long-range dependencies and are observed at non-uniform intervals. In these settings, traditional sequence-based recurrent models struggle. To overcome this, researchers often…

Homomorphic encryption (HE) is a promising technique used for privacy-preserving computation. Since HE schemes only support primitive polynomial operations, homomorphic evaluation of polynomial approximations for non-polynomial functions…

Privacy-preserving machine learning has become an important long-term pursuit in this era of artificial intelligence (AI). Fully Homomorphic Encryption (FHE) is a uniquely promising solution, offering provable privacy and security…

Homomorphic encryption (HE)---the ability to perform computation on encrypted data---is an attractive remedy to increasing concerns about data privacy in deep learning (DL). However, building DL models that operate on ciphertext is…

Recently, large-scale transformer-based models have been proven to be effective over various tasks across many domains. Nevertheless, applying them in industrial production requires tedious and heavy works to reduce inference costs. To fill…