相关论文: Memory-Efficient Deep Learning Inference in Truste…

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…

Trusted execution environments (TEEs) provide an environment for running workloads in the cloud without having to trust cloud service providers, by offering additional hardware-assisted security guarantees. However, main memory encryption…

Combining Federated Learning (FL) with a Trusted Execution Environment (TEE) is a promising approach for realizing privacy-preserving FL, which has garnered significant academic attention in recent years. Implementing the TEE on the server…

Heterogeneous collaborative computing with NPU and CPU has received widespread attention due to its substantial performance benefits. To ensure data confidentiality and integrity during computing, Trusted Execution Environments (TEE) is…

Deep Neural Network (DNN) models are usually trained sequentially from one layer to another, which causes forward, backward and update locking's problems, leading to poor performance in terms of training time. The existing parallel…

Privacy-preserving solutions enable companies to offload confidential data to third-party services while fulfilling their government regulations. To accomplish this, they leverage various cryptographic techniques such as Homomorphic…

Trusted Execution Environments (TEEs) are used to protect sensitive data and run secure execution for security-critical applications, by providing an environment isolated from the rest of the system. However, over the last few years, TEEs…

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…

The distributed (federated) LLM is an important method for co-training the domain-specific LLM using siloed data. However, maliciously stealing model parameters and data from the server or client side has become an urgent problem to be…

Fully-connected layers in deep neural networks (DNN) are often the throughput and power bottleneck during training. This is due to their large size and low data reuse. Pruning dense layers can significantly reduce the size of these…

The growing replication crisis across disciplines such as economics, finance, and other social sciences as well as computer science undermines the credibility of academic research. Current institutional solutions -- such as artifact…

Deep neural networks (DNNs) have been quite successful in solving many complex learning problems. However, DNNs tend to have a large number of learning parameters, leading to a large memory and computation requirement. In this paper, we…

The deployment of large language models (LLMs) on third-party devices requires new ways to protect model intellectual property. While Trusted Execution Environments (TEEs) offer a promising solution, their performance limits can lead to a…

We propose a reconfigurable hardware architecture for deep neural networks (DNNs) capable of online training and inference, which uses algorithmically pre-determined, structured sparsity to significantly lower memory and computational…

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…

Trusted Execution Environments (TEEs) are a feature of modern central processing units (CPUs) that aim to provide a high assurance, isolated environment in which to run workloads that demand both confidentiality and integrity. Hardware and…

Deploying deep neural networks (DNNs) on edge devices exposes valuable intellectual property to model-stealing attacks. While TEE-shielded DNN partitioning (TSDP) mitigates this by isolating sensitive computations, existing paradigms fail…

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…

Existing methods for reducing the computational burden of neural networks at run-time, such as parameter pruning or dynamic computational path selection, focus solely on improving computational efficiency during inference. On the other…

Deep Ensembles (DE) are a prominent approach for achieving excellent performance on key metrics such as accuracy, calibration, uncertainty estimation, and out-of-distribution detection. However, hardware limitations of real-world systems…