Related papers: Flash: A Hybrid Private Inference Protocol for Dee…

Private Transformer inference using cryptographic protocols offers promising solutions for privacy-preserving machine learning; however, it still faces significant runtime overhead (efficiency issues) and challenges in handling long-token…

Private Inference (PI) enables deep neural networks (DNNs) to work on private data without leaking sensitive information by exploiting cryptographic primitives such as multi-party computation (MPC) and homomorphic encryption (HE). However,…

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…

Large deep learning models have demonstrated strong ability to solve many tasks across a wide range of applications. Those large models typically require training and inference to be distributed. Tensor parallelism is a common technique…

Among hardware accelerators for deep-learning inference, data flow implementations offer low latency and high throughput capabilities. In these architectures, each neuron is mapped to a dedicated hardware unit, making them well-suited for…

Homomorphic encryption (HE) is a privacy-preserving computation technique that enables computation on encrypted data. Today, the potential of HE remains largely unrealized as it is impractically slow, preventing it from being used in real…

Homomorphic encryption (HE)-based deep neural network (DNN) inference protects data and model privacy but suffers from significant computation overhead. We observe transforming the DNN weights into circulant matrices converts general…

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…

Billions of text analysis requests containing private emails, personal text messages, and sensitive online reviews, are processed by recurrent neural networks (RNNs) deployed on public clouds every day. Although prior secure networks…

In this paper, we introduce a privacy-preserving stable diffusion framework leveraging homomorphic encryption, called HE-Diffusion, which primarily focuses on protecting the denoising phase of the diffusion process. HE-Diffusion is a…

The growing popularity of cloud-based machine learning raises a natural question about the privacy guarantees that can be provided in such a setting. Our work tackles this problem in the context where a client wishes to classify private…

Machine Learning as a Service (MLaaS) exposes sensitive client data to service providers. Private inference mitigates this risk while preserving model functionality. Despite extensive progress in MPC-based solutions, they remain constrained…

Large pre-trained Vision-Language Models (VLMs), such as Contrastive Language-Image Pre-training (CLIP), have exhibited remarkable zero-shot performance across various image classification tasks. Fine-tuning these models on domain-specific…

This paper presents an efficient framework for private Transformer inference that combines Homomorphic Encryption (HE) and Secure Multi-party Computation (MPC) to protect data privacy. Existing methods often leverage HE for linear layers…

Spectral-domain CNNs have been shown to be more efficient than traditional spatial CNNs in terms of reducing computation complexity. However they come with a `kernel explosion' problem that, even after compression (pruning), imposes a high…

In this paper, we investigate a problem of minimizing total energy consumption for secure federated learning (FL) over wireless edge networks. To address the high computational cost and privacy challenges in conventional FL with neural…

The success of deep neural networks (DNN) in machine perception applications such as image classification and speech recognition comes at the cost of high computation and storage complexity. Inference of uncompressed large scale DNN models…

Light-weight convolutional neural networks (CNNs) have small complexity and are good candidates for low-power, high-throughput inference. Such networks are heterogeneous in terms of computation-to-communication (CTC) ratios and computation…

Deep convolution Neural Network (DCNN) has been widely used in computer vision tasks. However, for edge devices even inference has too large computational complexity and data access amount. The inference latency of state-of-the-art models…

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…