Related papers: Ditto: Quantization-aware Secure Inference of Tran…

On-device inference offers privacy, offline use, and instant response, but consumer hardware restricts large language models (LLMs) to low throughput and capability. To overcome this challenge, we present prima.cpp, a distributed on-device…

In this work, we present novel protocols over rings for semi-honest secure three-party computation (3PC) and malicious four-party computation (4PC) with one corruption. While most existing works focus on improving total communication…

We introduce Monte-Carlo Attention (MCA), a randomized approximation method for reducing the computational cost of self-attention mechanisms in Transformer architectures. MCA exploits the fact that the importance of each token in an input…

Classical Distributed Model Predictive Control (DiMPC) requires multiple iterations to achieve convergence, leading to high computational and communication burdens. This work focuses on the improvement of an iteration-free distributed MPC…

Deep learning as a means to inferencing has proliferated thanks to its versatility and ability to approach or exceed human-level accuracy. These computational models have seemingly insatiable appetites for computational resources not only…

We present CrypTFlow, a first of its kind system that converts TensorFlow inference code into Secure Multi-party Computation (MPC) protocols at the push of a button. To do this, we build three components. Our first component, Athos, is an…

High-frequency inductive power transfer (IPT) has garnered significant attention in recent years due to its long transmission distance and high efficiency. The inductance values L and quality factors Q of the transmitting and receiving…

Privacy-preserving machine learning (PPML) aims at enabling machine learning (ML) algorithms to be used on sensitive data. We contribute to this line of research by proposing a framework that allows efficient and secure evaluation of…

Large language models (LLMs) have demonstrated remarkable capabilities in various kinds of tasks, while the billion or even trillion parameters bring storage and efficiency bottlenecks for inference. Quantization, particularly…

Secure Multi-Party Computation (SMC) allows parties with similar background to compute results upon their private data, minimizing the threat of disclosure. The exponential increase in sensitive data that needs to be passed upon networked…

In this paper, we present a robust adaptive model predictive control (MPC) scheme for linear systems subject to parametric uncertainty and additive disturbances. The proposed approach provides a computationally efficient formulation with…

With the increasing demands for privacy protection, many privacy-preserving machine learning systems were proposed in recent years. However, most of them cannot be put into production due to their slow training and inference speed caused by…

This paper presents a parallel Monte Carlo simulation based performance quantification method for nonlinear model predictive control (NMPC) in closed-loop. The method provides distributions for the controller performance in stochastic…

Real-world applications are now processing big-data sets, often bottlenecked by the data movement between the compute units and the main memory. Near-memory computing (NMC), a modern data-centric computational paradigm, can alleviate these…

In cryptography, secure Multi-Party Computation (MPC) protocols allow participants to compute a function jointly while keeping their inputs private. Recent breakthroughs are bringing MPC into practice, solving fundamental challenges for…

Multi-Party Computation (MPC) is a technique enabling data from several sources to be used in a secure computation revealing only the result while protecting the original data, facilitating shared utilization of data sets gathered by…

Privacy-preserving data mining has become an important topic. People have built several multi-party-computation (MPC)-based frameworks to provide theoretically guaranteed privacy, the poor performance of real-world algorithms have always…

Pretraining transformers are generally time-consuming. Fully quantized training (FQT) is a promising approach to speed up pretraining. However, most FQT methods adopt a quantize-compute-dequantize procedure, which often leads to suboptimal…

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…

When applying machine learning to sensitive data, one has to find a balance between accuracy, information security, and computational-complexity. Recent studies combined Homomorphic Encryption with neural networks to make inferences while…