{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T22:40:58Z","timestamp":1780612858011,"version":"3.54.1"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890445","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["LoRATEE: A Secure and Efficient Inference Framework for Multi-Tenant LoRA LLMs Based on TEE"],"prefix":"10.1109","author":[{"given":"Zechao","family":"Lin","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China,100085"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sisi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China,100085"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingbin","family":"Wang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China,100085"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yulan","family":"Su","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China,100085"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Wang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China,100085"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Hou","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China,100085"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan","family":"Meng","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China,100085"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3605943"},{"issue":"5","key":"ref2","article-title":"Gpt-4 technical report. arxiv 2303.08774","volume":"2","year":"2023","journal-title":"View in Article"},{"key":"ref3","article-title":"Llumnix: Dynamic scheduling for large language model serving","author":"Sun","year":"2024"},{"key":"ref4","article-title":"Pie: Pooling cpu memory for llm inference","author":"Xu","year":"2024"},{"key":"ref5","article-title":"Conserve: Harvesting gpus for low-latency and high-throughput large language model serving","author":"Qiao","year":"2024"},{"key":"ref6","first-page":"27 730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref7","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref8","article-title":"Longlora: Efficient fine-tuning of long-context large language models","author":"Chen","year":"2023"},{"key":"ref9","article-title":"Qlora: Efficient finetuning of quantized llms","volume":"36","author":"Dettmers","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","article-title":"Peft: State-of-the-art parameter-efficient fine-tuning methods","author":"Mangrulkar","year":"2022"},{"key":"ref11","first-page":"1","article-title":"Punica: Multi-tenant lora serving","volume-title":"Proceedings of Machine Learning and Systems","volume":"6","author":"Chen"},{"key":"ref12","article-title":"S-lora: Serving thousands of concurrent lora adapters","author":"Sheng","year":"2023"},{"key":"ref13","article-title":"Caraserve: Cpu-assisted and rank-aware lora serving for generative llm inference","author":"Li","year":"2024"},{"key":"ref14","article-title":"Efficient multi-task llm quantization and serving for multiple lora adapters","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Xia"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2948618.2954330"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-816197-5.00008-5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2021.3126315"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2487726.2488368"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446717"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3536168.3543299"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.14778\/3583140.3583158"},{"key":"ref22","article-title":"One-for-all: Generalized lora for parameter-efficient fine-tuning","author":"Chavan","year":"2023"},{"key":"ref23","article-title":"Lorahub: Efficient cross-task generalization via dynamic lora composition","author":"Huang","year":"2023"},{"key":"ref24","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref25","first-page":"4051","article-title":"{AEX-Notify}: Thwarting precise {Single-Stepping} attacks through interrupt awareness for intel {SGX} enclaves","volume-title":"32nd USENIX Security Symposium (USENIX Security 23)","author":"Constable"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP57164.2023.00035"},{"key":"ref27","article-title":"Amd memory encryption","volume":"13","author":"Kaplan","year":"2016","journal-title":"White paper"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3711650.3711651"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3291047"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3567483"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3577923.3583648"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2023.3256796"},{"key":"ref33","first-page":"arXiv","article-title":"Confidential computing on nvidia h100 gpu: A performance benchmark study","author":"Zhu","year":"2024"},{"key":"ref34","article-title":"Slalom: Fast, verifiable and private execution of neural networks in trusted hardware","author":"Tramer","year":"2018"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/SP46215.2023.10179382"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323746"},{"key":"ref37","first-page":"663","article-title":"{AlpaServe}: Statistical multiplexing with model parallelism for deep learning serving","volume-title":"17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23)","author":"Li"},{"key":"ref38","first-page":"787","article-title":"{SHEPHERD}: Serving {DNNs} in the wild","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Zhang"},{"key":"ref39","article-title":"Blockllm: Multi-tenant finer-grained serving for large language models","author":"Li","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3315508.3329973"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref42","first-page":"521","article-title":"Orca: A distributed serving system for {Transformer-Based} models","volume-title":"16th USENIX generative Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Yu"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.544"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890445.pdf?arnumber=10890445","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:06Z","timestamp":1774416246000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890445\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890445","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}