相关论文: Cascade: Token-Sharded Private LLM Inference

Secure multi-party computation provides a wide array of protocols for mutually distrustful parties be able to securely evaluate functions of private inputs. Within recent years, many such protocols have been proposed representing a plethora…

The application of secure multiparty computation (MPC) in machine learning, especially privacy-preserving neural network training, has attracted tremendous attention from the research community in recent years. MPC enables several data…

We consider an edge computing scenario where users want to perform a linear computation on local, private data and a network-wide, public matrix. Users offload computations to edge servers located at the edge of the network, but do not want…

Personalized Large Language Models (LLMs) have become increasingly prevalent, showcasing the impressive capabilities of models like GPT-4. This trend has also catalyzed extensive research on deploying LLMs on mobile devices. Feasible…

Secure multiparty computation (SMC) is a promising technology for privacy-preserving collaborative computation. In the last years several feasibility studies have shown its practical applicability in different fields. However, it is…

In this paper, we consider a secure multi-party computation problem (MPC), where the goal is to offload the computation of an arbitrary polynomial function of some massive private matrices (inputs) to a cluster of workers. The workers are…

Speculative decoding has emerged as a promising lossless approach for accelerating Large Language Models (LLMs). As reasoning LLMs increasingly suffer from decode-stage overhead and approximation-based methods degrade accuracy, lossless…

Internet of Things devices are expanding rapidly and generating huge amount of data. There is an increasing need to explore data collected from these devices. Collaborative learning provides a strategic solution for the Internet of Things…

Recent advances in large language models (LLMs) have intensified the need to deliver both rapid responses and high-quality outputs. More powerful models yield better results but incur higher inference latency, whereas smaller models are…

An efficient paradigm for multi-party computation (MPC) are protocols structured around access to shared pre-processed computational resources. In this model, certain forms of correlated randomness are distributed to the participants prior…

Network intrusion is a well-studied area of cyber security. Current machine learning-based network intrusion detection systems (NIDSs) monitor network data and the patterns within those data but at the cost of presenting significant issues…

Unlike other industries in which intellectual property is patentable, the financial industry relies on trade secrecy to protect its business processes and methods, which can obscure critical financial risk exposures from regulators and the…

Logistic regression is an algorithm widely used for binary classification in various real-world applications such as fraud detection, medical diagnosis, and recommendation systems. However, training a logistic regression model with data…

The Key-Value (KV) cache, which stores intermediate attention computations (Key and Value pairs) to avoid redundant calculations, is a fundamental mechanism for accelerating Large Language Model (LLM) inference. However, this efficiency…

In this paper, we present a secure multiparty computation (SMC) protocol for single-source shortest distances (SSSD) in undirected graphs, where the location of edges is public, but their length is private. The protocol works in the…

To preserve data privacy, multi-party computation (MPC) enables executing Machine Learning (ML) algorithms on private data. However, MPC frameworks do not include optimized operations on sparse data. This absence makes them unsuitable for…

The computation of collision probability ($\mathcal{P}_c$) is crucial for space environmentalism and sustainability by providing decision-making knowledge that can prevent collisions between anthropogenic space objects. However, the…

We present S3ML, a secure serving system for machine learning inference in this paper. S3ML runs machine learning models in Intel SGX enclaves to protect users' privacy. S3ML designs a secure key management service to construct flexible…

Multi-party learning is an indispensable technique for improving the learning performance via integrating data from multiple parties. Unfortunately, directly integrating multi-party data would not meet the privacy preserving requirements.…

Private record linkage (PRL) is the problem of identifying pairs of records that are similar as per an input matching rule from databases held by two parties that do not trust one another. We identify three key desiderata that a PRL…