{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T05:06:04Z","timestamp":1773378364619,"version":"3.50.1"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Institute for Information & communications Technology Planning & Evaluation","award":["RS-2023-00261068"],"award-info":[{"award-number":["RS-2023-00261068"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3668872","type":"journal-article","created":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T20:50:25Z","timestamp":1772225425000},"page":"35705-35720","source":"Crossref","is-referenced-by-count":0,"title":["Personal Embedding Transformation for Privacy-Preserving Split Learning on Textual Data"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1008-2814","authenticated-orcid":false,"given":"Jungin","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Applied Artificial Intelligence, Hanyang University, Ansan, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0978-3657","authenticated-orcid":false,"given":"Yushin","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Hanyang University, Ansan, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1847-6088","authenticated-orcid":false,"given":"Sunghyun","family":"Cho","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Hanyang University, ERICA Campus, Ansan, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/twc.2019.2946140"},{"key":"ref2","first-page":"770","article-title":"Deep residual learning for image recognition","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"He"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106384"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/fi11040094"},{"key":"ref5","article-title":"Large language models for robotics: A survey","author":"Zeng","year":"2023","journal-title":"arXiv:2311.07226"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2426656.2426663"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3712016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11010016"},{"key":"ref9","first-page":"601","article-title":"Stealing machine learning models via prediction APIs","volume-title":"Proc. 25th USENIX Secur. Symp. (USENIX Secur.)","author":"Tram\u00e8r"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-70604-3_4"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20825"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3559613.3563201"},{"key":"ref13","first-page":"12130","article-title":"A stealthy wrongdoer: Feature-oriented reconstruction attack against split learning","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Xu"},{"key":"ref14","article-title":"Feature space hijacking attacks against differentially private split learning","author":"Gawron","year":"2022","journal-title":"arXiv:2201.04018"},{"key":"ref15","article-title":"Model inversion in split learning for personalized LLMs: New insights from information bottleneck theory","author":"Shu","year":"2025","journal-title":"arXiv:2501.05965"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.765"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref18","article-title":"A split-and-privatize framework for large language model fine-tuning","author":"Shen","year":"2023","journal-title":"arXiv:2312.15603"},{"key":"ref19","first-page":"5271","article-title":"PCAT: Functionality and data stealing from split learning by pseudo-client attack","volume-title":"Proc. 32nd USENIX Secur. Symp. (USENIX Secur.)","author":"Gao"},{"key":"ref20","article-title":"Mitigating privacy risks in llm embeddings from embedding inversion","author":"Liu","year":"2024","journal-title":"arXiv:2411.05034"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-71522-9_752"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/mwc.015.2200462"},{"key":"ref23","first-page":"34281","article-title":"Split-and-denoise: Protect large language model inference with local differential privacy","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mai"},{"key":"ref24","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016","journal-title":"arXiv:1609.07843"},{"issue":"8","key":"ref25","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref26","article-title":"AG news and IMDB","volume-title":"IEEE Dataport","author":"Li","year":"2024"},{"issue":"140","key":"ref27","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref28","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref30","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin"},{"key":"ref31","first-page":"1205","article-title":"Optimal kernel choice for large-scale two-sample tests","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Gretton"},{"key":"ref32","first-page":"97","article-title":"Learning transferable features with deep adaptation networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Long"},{"key":"ref33","article-title":"Model inversion attacks: A survey of approaches and countermeasures","author":"Zhou","year":"2024","journal-title":"arXiv:2411.10023"},{"key":"ref34","article-title":"UMAP: Uniform manifold approximation and projection for dimension reduction","author":"McInnes","year":"2018","journal-title":"arXiv:1802.03426"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11415613.pdf?arnumber=11415613","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:38:30Z","timestamp":1773347910000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11415613\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3668872","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}