Related papers: Nimbus: Secure and Efficient Two-Party Inference f…

Two-party computation (2PC) is promising to enable privacy-preserving deep learning (DL). However, the 2PC-based privacy-preserving DL implementation comes with high comparison protocol overhead from the non-linear operators. This work…

To enhance the computational efficiency of quantized Transformers, we replace the dot-product and Softmax-based attention with an alternative mechanism involving addition and ReLU activation only. This side-steps the expansion to double…

In this manuscript, we explore the application of model-free reinforcement learning in optimizing secure multiparty computation (SMPC) protocols. SMPC is a crucial tool for performing computations on private data without the need to…

In this study, we propose a two-party computation protocol for approximate matrix multiplication of fixed-point numbers. The proposed protocol is provably secure under standard lattice-based cryptographic assumptions and enables matrix…

Secure Multi-party Computation (MPC) enables untrusted parties to jointly compute a function without revealing their inputs. Its application to machine learning (ML) has gained significant attention, particularly for secure inference…

Diffusion Models (DMs) achieve state-of-the-art synthesis results in image generation and have been applied to various fields. However, DMs sometimes seriously violate user privacy during usage, making the protection of privacy an urgent…

Recent advances in state-of-the-art DNN architecture design have been moving toward Transformer models. These models achieve superior accuracy across a wide range of applications. This trend has been consistent over the past several years…

Transformers are mostly relying on softmax attention, which introduces quadratic complexity with respect to sequence length and remains a major bottleneck for efficient inference. Prior work on linear or hybrid attention typically replaces…

Transformer models rely on High-Performance Computing (HPC) resources for inference, where soft errors are inevitable in large-scale systems, making the reliability of the model particularly critical. Existing fault tolerance frameworks for…

With the growing deployment of pre-trained models like Transformers on cloud platforms, privacy concerns about model parameters and inference data are intensifying. Existing Privacy-Preserving Transformer Inference (PPTI) frameworks face…

Federated machine learning systems have been widely used to facilitate the joint data analytics across the distributed datasets owned by the different parties that do not trust each others. In this paper, we proposed a novel Gradient…

The concrete efficiency of secure computation has been the focus of many recent works. In this work, we present concretely-efficient protocols for secure $3$-party computation (3PC) over a ring of integers modulo $2^{\ell}$ tolerating one…

In this work, we present an efficient secure multi-party computation MPC protocol that provides strong security guarantees in settings with dishonest majority of participants who may behave arbitrarily. Unlike the popular MPC implementation…

Non-linear operations such as GELU, Layer normalization, and Softmax are essential yet costly building blocks of Transformer models. Several prior works simplified these operations with look-up tables or integer computations, but such…

Many inference services based on large language models (LLMs) pose a privacy concern, either revealing user prompts to the service or the proprietary weights to the user. Secure inference offers a solution to this problem through secure…

In this work, we consider the problem of secure multi-party computation (MPC), consisting of $\Gamma$ sources, each has access to a large private matrix, $N$ processing nodes or workers, and one data collector or master. The master is…

Parameter-efficient fine-tuning (PEFT) allows model builders to capture the task-specific parameters into adapters, which are a fraction of the size of the original base model. Popularity of PEFT technique for fine-tuning has led to the…

Softmax is widely used in deep learning to map some representation to a probability distribution. As it is based on exp/log functions that are relatively expensive in multi-party computation, Mohassel and Zhang (2017) proposed a simpler…

Secure multi-party computation (MPC) allows a set of parties to compute a function jointly while keeping their inputs private. Compared with the MPC based on garbled circuits,some recent research results show that MPC based on secret…

Machine Learning as a Service (MLaaS) is an increasingly popular design where a company with abundant computing resources trains a deep neural network and offers query access for tasks like image classification. The challenge with this…