Related papers: Evaluating the Performance of the DeepSeek Model i…

Large Language Models (LLMs) have emerged as powerful tools for tackling a wide range of problems, including those in scientific computing, particularly in solving partial differential equations (PDEs). However, different models exhibit…

As cloud-based ML expands, ensuring data security during training and inference is critical. GPU-based Trusted Execution Environments (TEEs) offer secure, high-performance solutions, with CPU TEEs managing data movement and GPU TEEs…

Fully Homomorphic Encryption (FHE) allows for computation directly on encrypted data and enables privacy-preserving neural inference in the cloud. Prior work has focused on models with dense inputs (e.g., CNNs), with less attention given to…

Trusted execution environments (TEEs) are an integral part of modern secure processors. They ensure that their application and code pages are confidential, tamper proof and immune to diverse types of attacks. In 2021, Intel suddenly…

The classification service over a stream of data is becoming an important offering for cloud providers, but users may encounter obstacles in providing sensitive data due to privacy concerns. While Trusted Execution Environments (TEEs) are…

Processing sensitive data, such as those produced by body sensors, on third-party untrusted clouds is particularly challenging without compromising the privacy of the users generating it. Typically, these sensors generate large quantities…

As edge devices gain stronger computing power, deploying high-performance DNN models on untrusted hardware has become a practical approach to cut inference latency and protect user data privacy. Given high model training costs and user…

A collaboration between dataset owners and model owners is needed to facilitate effective machine learning (ML) training. During this collaboration, however, dataset owners and model owners want to protect the confidentiality of their…

Federated Learning (FL) opens new perspectives for training machine learning models while keeping personal data on the users premises. Specifically, in FL, models are trained on the users devices and only model updates (i.e., gradients) are…

Today, machine learning is widely applied in sensitive, security-related, and financially lucrative applications. Model extraction attacks undermine current business models where a model owner sells model access, e.g., via MLaaS APIs.…

Deploying large language models (LLMs) as cloud services raises privacy concerns as inference may leak sensitive data. Fully Homomorphic Encryption (FHE) allows computation on encrypted data, but current FHE methods struggle with efficient…

This work addresses the timely yet underexplored problem of performing inference and finetuning of a proprietary LLM owned by a model provider entity on the confidential/private data of another data owner entity, in a way that ensures the…

As Edge Intelligence (EI) becomes increasingly prevalent in domains such as smart healthcare, manufacturing, and critical infrastructure, ensuring data privacy while maintaining system efficiency is a growing challenge. This paper presents…

Privacy and security-related concerns are growing as machine learning reaches diverse application domains. The data holders want to train with private data while exploiting accelerators, such as GPUs, that are hosted in the cloud. However,…

Both AMD and Intel have presented technologies for confidential computing in cloud environments. The proposed solutions - AMD SEV (-ES, -SNP) and Intel TDX - protect Virtual Machines (VMs) against attacks from higher privileged layers…

With the widespread application of large language models (LLMs) in the field of code intelligence, increasing attention has been paid to the reliability and controllability of their outputs in code reasoning tasks. Confidence estimation…

Numerous companies have started offering services based on large language models (LLM), such as ChatGPT, which inevitably raises privacy concerns as users' prompts are exposed to the model provider. Previous research on secure reasoning…

Confidential computing on GPUs, like NVIDIA H100, mitigates the security risks of outsourced Large Language Models (LLMs) by implementing strong isolation and data encryption. Nonetheless, this encryption incurs a significant performance…

Performing deep learning on end-user devices provides fast offline inference results and can help protect the user's privacy. However, running models on untrusted client devices reveals model information which may be proprietary, i.e., the…

In this paper, we address the problem of efficiently answering predicate queries on encrypted databases, those secured by Trusted Execution Environments (TEEs), which enable untrusted providers to process encrypted user data without…