{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T21:18:15Z","timestamp":1768425495709,"version":"3.49.0"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Eighth Research Institute of China Aerospace Science and Technology Group Company, Ltd.","award":["USCAST2023-17"],"award-info":[{"award-number":["USCAST2023-17"]}]},{"name":"Eighth Research Institute of China Aerospace Science and Technology Group Company, Ltd.","award":["USCAST2023-21"],"award-info":[{"award-number":["USCAST2023-21"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1109\/tai.2024.3429480","type":"journal-article","created":{"date-parts":[[2024,7,17]],"date-time":"2024-07-17T13:30:32Z","timestamp":1721223032000},"page":"405-415","source":"Crossref","is-referenced-by-count":5,"title":["LLMaaS: Serving Large-Language Models on Trusted Serverless Computing Platforms"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9373-8474","authenticated-orcid":false,"given":"Zinuo","family":"Cai","sequence":"first","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1277-8512","authenticated-orcid":false,"given":"Rongbo","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0357-9062","authenticated-orcid":false,"given":"Yicheng","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9800-1068","authenticated-orcid":false,"given":"Weishan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Qingdao Institute of Software, College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9592-8490","authenticated-orcid":false,"given":"Ruhui","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4714-7400","authenticated-orcid":false,"given":"Haibing","family":"Guan","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00051"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441578"},{"key":"ref3","first-page":"521","article-title":"Orca: A distributed serving system for transformer-based generative models","volume-title":"Proc. 16th USENIX Symp. Oper. Syst. Des. Implementation (OSDI)","author":"Yu","year":"2022"},{"issue":"10","key":"ref4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3659100","article-title":"The serverless computing survey: A technical primer for design architecture","volume":"54","author":"Li","year":"2022","journal-title":"ACM Comput. Surv."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2022.3166553"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS51616.2021.00022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2023.3294406"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507709"},{"key":"ref9","article-title":"Tetris: Memory-efficient serverless inference through tensor sharing","volume-title":"Proc. USENIX Annu. Tech. Conf. (USENIX ATC)","author":"Li","year":"2022"},{"key":"ref10","first-page":"1049","article-title":"Mark: Exploiting cloud services for cost-effective, slo-aware machine learning inference serving","volume-title":"Proc. USENIX Annu. Tech. Conf. (USENIX ATC)","author":"Zhang","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421285"},{"key":"ref12","first-page":"443","article-title":"Serving DNNs like clockwork: Performance predictability from the bottom up","volume-title":"Proc. 14th USENIX Symp. Oper. Syst. Des. Implementation (OSDI)","author":"Gujarati","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3280970"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS46320.2019.00042"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/83"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3288985"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.103061"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.001.2300140"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796841"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486990"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-022-00756-z"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2022.3205665"},{"key":"ref23","article-title":"Intel SGX explained","author":"Costan","year":"2016","journal-title":"Cryptol. ePrint Arch."},{"key":"ref24","first-page":"1450","article-title":"Strengthening VM isolation with integrity protection and more","volume":"53","author":"Sev-Snp","year":"2020","journal-title":"White Paper"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/EI256261.2022.10116101"},{"key":"ref26","article-title":"SoK: Machine learning with confidential computing","author":"Mo","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3512892"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2023.3262289"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2948618.2954330"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3300061.3345447"},{"key":"ref31","article-title":"TensorSCONE: A secure TensorFlow framework using intel SGX","author":"Kunkel","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486998"},{"key":"ref33","first-page":"645","article-title":"$\\{$Graphene-SGX$\\}$: A practical library $\\{$OS$\\}$ for unmodified applications on $\\{$SGX$\\}$","volume-title":"Proc. USENIX Annu. Tech. Conf. (USENIX ATC)","author":"Tsai","year":"2017"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ms.2024.3406333"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICSP56322.2022.9965295"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2019.2894621"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TSUSC.2023.3311197"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2017.09.001"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-015-1945-5"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9078688\/10908727\/10601537.pdf?arnumber=10601537","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:09:40Z","timestamp":1755911380000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10601537\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":39,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tai.2024.3429480","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}