{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T15:18:10Z","timestamp":1783178290767,"version":"3.54.6"},"reference-count":46,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100010418","name":"Institute for Information and Communications Technology Promotion","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Korea Ministry of Science and ICT","doi-asserted-by":"publisher","award":["IITP-2026-RS-2024-00438239"],"award-info":[{"award-number":["IITP-2026-RS-2024-00438239"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Korea Ministry of Science and ICT","doi-asserted-by":"publisher","award":["RS-2024-00509257"],"award-info":[{"award-number":["RS-2024-00509257"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Systems Architecture"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.sysarc.2026.103844","type":"journal-article","created":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T15:54:57Z","timestamp":1779206097000},"page":"103844","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["ADPSL: Adaptive and privacy preserving dynamic split learning for lightweight transformer models on heterogeneous IoT devices"],"prefix":"10.1016","volume":"177","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2953-7314","authenticated-orcid":false,"given":"Md Nahid","family":"Sultan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tran Hoang","family":"Hai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0184-6975","authenticated-orcid":false,"given":"Eui-Nam","family":"Huh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.sysarc.2026.103844_b1","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.sysarc.2026.103844_b2","doi-asserted-by":"crossref","first-page":"681","DOI":"10.1007\/s11023-020-09548-1","article-title":"GPT-3: Its nature, scope, limits, and consequences","volume":"30","author":"Floridi","year":"2020","journal-title":"Minds Mach."},{"key":"10.1016\/j.sysarc.2026.103844_b3","series-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"issue":"240","key":"10.1016\/j.sysarc.2026.103844_b4","first-page":"1","article-title":"PaLM: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.sysarc.2026.103844_b5","series-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"10.1016\/j.sysarc.2026.103844_b6","series-title":"A comprehensive survey of AI-generated content (AIGC): A history of generative AI from GAN to ChatGPT","author":"Cao","year":"2023"},{"key":"10.1016\/j.sysarc.2026.103844_b7","series-title":"Transformers in medical imaging: A survey","author":"Shamshad","year":"2022"},{"key":"10.1016\/j.sysarc.2026.103844_b8","doi-asserted-by":"crossref","unstructured":"S. Zheng, J. Lu, H. Zhao, X. Zhu, Z. Luo, Y. Wang, Y. Fu, J. Feng, T. Xiang, P.H.S. Torr, Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers, in: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2021, pp. 6881\u20136890.","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"10.1016\/j.sysarc.2026.103844_b9","doi-asserted-by":"crossref","unstructured":"S. Bhojanapalli, A. Chakrabarti, D. Glasner, D. Li, T. Unterthiner, A. Veit, Understanding robustness of transformers for image classification, in: Proc. IEEE\/CVF International Conference on Computer Vision, ICCV, 2021, pp. 10231\u201310241.","DOI":"10.1109\/ICCV48922.2021.01007"},{"issue":"8","key":"10.1016\/j.sysarc.2026.103844_b10","doi-asserted-by":"crossref","first-page":"1384","DOI":"10.3390\/diagnostics11081384","article-title":"TransMed: Transformers advance multi-modal medical image classification","volume":"11","author":"Dai","year":"2021","journal-title":"Diagnostics"},{"key":"10.1016\/j.sysarc.2026.103844_b11","series-title":"MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer","author":"Mehta","year":"2021"},{"key":"10.1016\/j.sysarc.2026.103844_b12","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1007\/s42488-020-00027-x","article-title":"Internet of things based distributed healthcare systems: A review","volume":"2","author":"Birje","year":"2020","journal-title":"J. Data Inf. Manag."},{"key":"10.1016\/j.sysarc.2026.103844_b13","series-title":"Towards the Integration of IoT, Cloud and Big Data: Services, Applications and Standards","first-page":"97","article-title":"Iot equipped intelligent distributed framework for smart healthcare systems","author":"Rani","year":"2023"},{"key":"10.1016\/j.sysarc.2026.103844_b14","doi-asserted-by":"crossref","first-page":"1454","DOI":"10.1016\/j.jclepro.2016.10.006","article-title":"A review of Internet of Things for smart home: Challenges and solutions","volume":"140","author":"Stojkoska","year":"2017","journal-title":"J. Clean. Prod."},{"key":"10.1016\/j.sysarc.2026.103844_b15","doi-asserted-by":"crossref","first-page":"1681","DOI":"10.22214\/ijraset.2017.8239","article-title":"Smart campus using IoT with Bangladesh perspective: A possibility and limitation","author":"Sultan","year":"2017","journal-title":"Int. J. Res. Appl. Sci. Eng. Technol."},{"key":"10.1016\/j.sysarc.2026.103844_b16","unstructured":"J. Kone\u010dn\u00fd, H.B. McMahan, D. Ramage, P. Richt\u00e1rik, Federated learning: Strategies for improving communication efficiency, in: Proc. NIPS Workshop on Private Multi-Party Machine Learning, 2016."},{"key":"10.1016\/j.sysarc.2026.103844_b17","series-title":"Federated and Transfer Learning","first-page":"7","article-title":"Federated learning for resource-constrained IoT devices: Panoramas and state of the art","author":"Imteaj","year":"2022"},{"key":"10.1016\/j.sysarc.2026.103844_b18","doi-asserted-by":"crossref","unstructured":"Y. Chen, Y. Ning, M. Slawski, H. Rangwala, Asynchronous online federated learning for edge devices with non-IID data, in: Proc. IEEE International Conference on Big Data, 2020, pp. 15\u201324.","DOI":"10.1109\/BigData50022.2020.9378161"},{"key":"10.1016\/j.sysarc.2026.103844_b19","unstructured":"J. Vepakomma, O. Gupta, T. Swedish, R. Raskar, Split learning for health: Distributed deep learning without sharing raw patient data, in: Proc. NeurIPS Workshops, 2018."},{"key":"10.1016\/j.sysarc.2026.103844_b20","unstructured":"A. Pasquini, G. Ateniese, M. Conti, Information leakage in split learning, in: Proc. IEEE Security and Privacy Workshops, 2021."},{"issue":"3","key":"10.1016\/j.sysarc.2026.103844_b21","article-title":"Split learning: An overview of architectures, applications, and privacy challenges","volume":"17","author":"Thapa","year":"2025","journal-title":"Future Internet"},{"key":"10.1016\/j.sysarc.2026.103844_b22","article-title":"ARES: Adaptive resource-aware split learning for Internet of Things","volume":"early access","author":"Samikwa","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.sysarc.2026.103844_b23","doi-asserted-by":"crossref","DOI":"10.1109\/TMLCN.2024.3409205","article-title":"DFL: Dynamic federated split learning in heterogeneous IoT","author":"Samikwa","year":"2024","journal-title":"IEEE Trans. Mach. Learn. Commun. Netw."},{"issue":"11","key":"10.1016\/j.sysarc.2026.103844_b24","doi-asserted-by":"crossref","first-page":"4301","DOI":"10.1109\/TCAD.2024.3438995","article-title":"EASTER: Learning to split transformers at the edge robustly","volume":"43","author":"Guo","year":"2024","journal-title":"IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."},{"key":"10.1016\/j.sysarc.2026.103844_b25","unstructured":"S. Mehta, M. Rastegari, MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer, in: Proc. ICLR, 2022."},{"key":"10.1016\/j.sysarc.2026.103844_b26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.jnca.2018.05.003","article-title":"Distributed learning of deep neural network over multiple agents","volume":"116","author":"Gupta","year":"2018","journal-title":"J. Netw. Comput. Appl."},{"key":"10.1016\/j.sysarc.2026.103844_b27","series-title":"End-to-end evaluation of federated learning and split learning for Internet of Things","author":"Gao","year":"2020"},{"issue":"10","key":"10.1016\/j.sysarc.2026.103844_b28","doi-asserted-by":"crossref","first-page":"2538","DOI":"10.1109\/TC.2021.3135752","article-title":"Evaluation and optimization of distributed machine learning techniques for Internet of Things","volume":"71","author":"Gao","year":"2021","journal-title":"IEEE Trans. Comput."},{"key":"10.1016\/j.sysarc.2026.103844_b29","series-title":"UnSplit: Data-oblivious model inversion, model stealing, and label inference attacks against split learning","author":"Erdogan","year":"2021"},{"key":"10.1016\/j.sysarc.2026.103844_b30","series-title":"EXACT: Extensive attack for split learning","author":"Qiu","year":"2023"},{"key":"10.1016\/j.sysarc.2026.103844_b31","series-title":"Similarity-based label inference attack against training and inference of split learning","author":"Liu","year":"2022"},{"key":"10.1016\/j.sysarc.2026.103844_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.132247","article-title":"Membership inference attacks against split inference via knowledge transfer","volume":"666","author":"Yi","year":"2026","journal-title":"Neurocomputing"},{"key":"10.1016\/j.sysarc.2026.103844_b33","series-title":"Proc. IEEE Consumer Communications and Networking Conference","article-title":"Federated split learning for human activity recognition with differential privacy","author":"Ndeko","year":"2025"},{"issue":"11","key":"10.1016\/j.sysarc.2026.103844_b34","doi-asserted-by":"crossref","first-page":"483","DOI":"10.5626\/KTCP.2025.31.11.483","article-title":"Real-time adaptive split learning via device-specific DNN partitioning for IoT intelligence on edge cloud","volume":"31","author":"Sultan","year":"2025","journal-title":"KIISE Trans. Comput. Pract."},{"key":"10.1016\/j.sysarc.2026.103844_b35","series-title":"Proc. International Conference on Ubiquitous Communication (Ucom)","first-page":"438","article-title":"FedsLLM: Federated split learning for large language models over communication networks","author":"Zhao","year":"2024"},{"key":"10.1016\/j.sysarc.2026.103844_b36","doi-asserted-by":"crossref","unstructured":"S. Zhang, G. Cheng, Z. Li, W. Wu, SplitLLM: Hierarchical split learning for large language model over wireless network, in: Proc. IEEE Global Communications Conference Workshops (GC Wkshps), Cape Town, South Africa, 2024, pp. 1\u20136, http:\/\/dx.doi.org\/10.1109\/GCWkshp64532.2024.11100350.","DOI":"10.1109\/GCWkshp64532.2024.11100350"},{"key":"10.1016\/j.sysarc.2026.103844_b37","series-title":"MSFusion: A dynamic model splitting approach for resource-constrained machines to collaboratively train larger models","author":"Xie","year":"2024"},{"key":"10.1016\/j.sysarc.2026.103844_b38","doi-asserted-by":"crossref","unstructured":"L. Wang, B. Shang, Y. Li, P. Mohapatra, W. Dong, X. Wang, Q. Zhu, Split adaptation for pre-trained vision transformers, in: Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition, CVPR, 2025, pp. 20092\u201320102.","DOI":"10.1109\/CVPR52734.2025.01871"},{"issue":"16","key":"10.1016\/j.sysarc.2026.103844_b39","doi-asserted-by":"crossref","first-page":"5983","DOI":"10.3390\/s22165983","article-title":"Combined federated and split learning in edge computing for ubiquitous intelligence in Internet of Things: State-of-the-art and future directions","volume":"22","author":"Duan","year":"2022","journal-title":"Sensors"},{"key":"10.1016\/j.sysarc.2026.103844_b40","series-title":"SplitFed: When federated learning meets split learning","author":"Thapa","year":"2020"},{"key":"10.1016\/j.sysarc.2026.103844_b41","unstructured":"A. Pasquini, S. Hassanpour, A. Gurses, Information leakage in split learning, in: Proc. IEEE Symposium on Security and Privacy Workshops, 2021."},{"issue":"3\u20134","key":"10.1016\/j.sysarc.2026.103844_b42","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1561\/0400000042","article-title":"The algorithmic foundations of differential privacy","volume":"9","author":"Dwork","year":"2014","journal-title":"Found. Trends Theor. Comput. Sci."},{"key":"10.1016\/j.sysarc.2026.103844_b43","doi-asserted-by":"crossref","unstructured":"M. Abadi, A. Chu, I. Goodfellow, H.B. McMahan, I. Mironov, K. Talwar, L. Zhang, Deep learning with differential privacy, in: Proc. ACM Conference on Computer and Communications Security, CCS, 2016, pp. 308\u2013318.","DOI":"10.1145\/2976749.2978318"},{"issue":"10","key":"10.1016\/j.sysarc.2026.103844_b44","doi-asserted-by":"crossref","first-page":"10200","DOI":"10.1109\/JIOT.2020.2987070","article-title":"Edge computing-enabled smart cities: A comprehensive survey","volume":"7","author":"Khan","year":"2020","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.sysarc.2026.103844_b45","series-title":"Jetson Nano Power Management","author":"NVIDIA","year":"2020"},{"key":"10.1016\/j.sysarc.2026.103844_b46","series-title":"Learning Multiple Layers of Features from Tiny Images","author":"Krizhevsky","year":"2009"}],"container-title":["Journal of Systems Architecture"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1383762126001621?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1383762126001621?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T14:42:13Z","timestamp":1783176133000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1383762126001621"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":46,"alternative-id":["S1383762126001621"],"URL":"https:\/\/doi.org\/10.1016\/j.sysarc.2026.103844","relation":{},"ISSN":["1383-7621"],"issn-type":[{"value":"1383-7621","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"ADPSL: Adaptive and privacy preserving dynamic split learning for lightweight transformer models on heterogeneous IoT devices","name":"articletitle","label":"Article Title"},{"value":"Journal of Systems Architecture","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.sysarc.2026.103844","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"103844"}}