Related papers: Confidential Computing on NVIDIA Hopper GPUs: A Pe…

Running LLMs on end devices has garnered significant attention recently due to their advantages in privacy preservation. With the advent of lightweight LLM models and specially designed GPUs, on-device LLM inference has achieved the…

Confidential Computing enhances privacy of data in-use through hardware-based Trusted Execution Environments (TEEs) that use attestation to verify their integrity, authenticity, and certain runtime properties, along with those of the…

The community explored to build private inference frameworks for transformer-based large language models (LLMs) in a server-client setting, where the server holds the model parameters and the client inputs its private data (or prompt) for…

Trusted Execution Environments (TEEs) are gradually adopted by major cloud providers, offering a practical option of \emph{confidential computing} for users who don't fully trust public clouds. TEEs use CPU-enabled hardware features to…

High-Performance Computing (HPC) in the public cloud democratizes the supercomputing power that most users cannot afford to purchase and maintain. Researchers have studied its viability, performance, and usability. However, HPC in the cloud…

The last decade has seen a shift in the computer systems industry where heterogeneous computing has become prevalent. Graphics Processing Units (GPUs) are now present in supercomputers to mobile phones and tablets. GPUs are used for…

Trusted Execution Environments (TEEs) are designed to protect the privacy and integrity of data in use. They enable secure data processing and sharing in peer-to-peer networks, such as vehicular ad hoc networks of autonomous vehicles,…

Protecting the privacy of input data is of growing importance as machine learning methods reach new application domains. In this paper, we provide a unified training and inference framework for large DNNs while protecting input privacy and…

Future improvements in large language model (LLM) services increasingly hinge on access to high-value professional knowledge rather than more generic web data. However, the data providers of this knowledge face a skewed tradeoff between…

Edge computing processes data where it is generated, enabling faster decisions, lower bandwidth usage, and improved privacy. However, edge devices typically operate under strict constraints on processing power, memory, and energy…

Large-scale systems that compute analytics over a fleet of devices must achieve high privacy and security standards while also meeting data quality, usability, and resource efficiency expectations. We present a next-generation federated…

In this paper, we propose a new secure machine learning inference platform assisted by a small dedicated security processor, which will be easier to protect and deploy compared to today's TEEs integrated into high-performance processors.…

Trusted execution environments (TEEs) such as \intelsgx facilitate the secure execution of an application on untrusted machines. Sadly, such environments suffer from serious limitations and performance overheads in terms of writing back…

We present IPU Trusted Extensions (ITX), a set of experimental hardware extensions that enable trusted execution environments in Graphcore's AI accelerators. ITX enables the execution of AI workloads with strong confidentiality and…

Mixture of Experts (MoE) LLMs, characterized by their sparse activation patterns, offer a promising approach to scaling language models while avoiding proportionally increasing the inference cost. However, their large parameter sizes…

Large language models (LLMs) power many modern applications, but serving them at scale remains costly and resource-intensive. Current server-centric systems overlook consumer-grade GPUs at the edge. We introduce SpecEdge, an edge-assisted…

It has been a long standing problem to securely outsource computation tasks to an untrusted party with integrity and confidentiality guarantees. While fully homomorphic encryption (FHE) is a promising technique that allows computations…

We present a holistic design for GPU-accelerated computation in TrustZone TEE. Without pulling the complex GPU software stack into the TEE, we follow a simple approach: record the CPU/GPU interactions ahead of time, and replay the…

Online LLM inference powers many exciting applications such as intelligent chatbots and autonomous agents. Modern LLM inference engines widely rely on request batching to improve inference throughput, aiming to make it cost-efficient when…

We present DarkneTZ, a framework that uses an edge device's Trusted Execution Environment (TEE) in conjunction with model partitioning to limit the attack surface against Deep Neural Networks (DNNs). Increasingly, edge devices (smartphones…