Secure Community Transformers: Private Pooled Data for LLMs

[PDF] arxiv.org

TensorTEE: Unifying Heterogeneous TEE Granularity for Efficient Secure Collaborative Tensor Computing

H Han, X Zheng, Y Wen, Y Hao, E Feng, L Liang… - arXiv preprint arXiv …, 2024 - arxiv.org
Heterogeneous collaborative computing with NPU and CPU has received widespread
attention due to its substantial performance benefits. To ensure data confidentiality and …
相关文章 所有 2 个版本

Secure and Efficient Sharing of Model Insights between Commercial Large Language Models

N Sriprasert, T Somchaiya, P Khamphanit, P Chaikiatsri… - 2024 - researchsquare.com
Rapid advancements in large language models (LLMs) require secure and efficient
mechanisms for sharing insights between different models, particularly when handling …
相关文章 所有 2 个版本