Related papers: SecureInfer: Heterogeneous TEE-GPU Architecture fo…

A number of trusted execution environments (TEEs) have been proposed by both academia and industry. However, most of them require specific hardware or firmware changes and are bound to specific hardware vendors (such as Intel, AMD, ARM, and…

To ensure secure and trustworthy execution of applications, vendors frequently embed trusted execution environments into their systems. Here, applications are protected from adversaries, including a malicious operating system. TEEs are…

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.…

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…

Trusted Execution Environments (TEEs), such as Intel Software Guard eXtensions (SGX), are considered as a promising approach to resolve security challenges in clouds. TEEs protect the confidentiality and integrity of application code and…

Federated Learning (FL) enables collaborative model training while preserving data privacy by keeping raw data locally stored on client devices, preventing access from other clients or the central server. However, recent studies reveal that…

Large language models(LLMs) are currently at the forefront of the machine learning field, which show a broad application prospect but at the same time expose some risks of privacy leakage. We combined Fully Homomorphic Encryption(FHE) and…

Hardware-enclaves that target complex CPU designs compromise both security and performance. Programs have little control over micro-architecture, which leads to side-channel leaks, and then have to be transformed to have worst-case control-…

With the increased usage of AI accelerators on mobile and edge devices, on-device machine learning (ML) is gaining popularity. Thousands of proprietary ML models are being deployed today on billions of untrusted devices. This raises serious…

Foundation Models (FMs) display exceptional performance in tasks such as natural language processing and are being applied across a growing range of disciplines. Although typically trained on large public datasets, FMs are often fine-tuned…

We propose and implement a Privacy-preserving Federated Learning ($PPFL$) framework for mobile systems to limit privacy leakages in federated learning. Leveraging the widespread presence of Trusted Execution Environments (TEEs) in high-end…

Heterogeneous computing, which incorporates GPUs, NPUs, and FPGAs, is increasingly utilized to improve the efficiency of computer systems. However, this shift has given rise to significant security and privacy concerns, especially when the…

To safeguard user data privacy, on-device inference has emerged as a prominent paradigm on mobile and Internet of Things (IoT) devices. This paradigm involves deploying a model provided by a third party on local devices to perform inference…

Federated learning has emerged as a popular paradigm for collaboratively training a model from data distributed among a set of clients. This learning setting presents, among others, two unique challenges: how to protect privacy of the…

Modern data centers have grown beyond CPU nodes to provide domain-specific accelerators such as GPUs and FPGAs to their customers. From a security standpoint, cloud customers want to protect their data. They are willing to pay additional…

Trusted Execution Environments (TEE) are used to safeguard on-device models. However, directly employing TEEs to secure the entire DNN model is challenging due to the limited computational speed. Utilizing GPU can accelerate DNN's…

Large Language Models (LLMs) are increasingly used in circuit design tasks and have typically undergone multiple rounds of training. Both the trained models and their associated training data are considered confidential intellectual…

Large language models (LLMs) are increasingly deployed in high-stakes domains, yet a unified treatment of their overlapping safety challenges remains lacking. We present SafeLM, a framework that jointly addresses four pillars of LLM safety:…

Encrypted AI using fully homomorphic encryption (FHE) provides strong privacy guarantees; but its slow performance has limited practical deployment. Recent works proposed ASICs to accelerate FHE, but require expensive advanced manufacturing…

We present a security framework that strengthens distributed machine learning by standardizing integrity protections across CPU and GPU platforms and significantly reducing verification overheads. Our approach co-locates integrity…