{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T14:51:06Z","timestamp":1782399066627,"version":"3.54.5"},"reference-count":128,"publisher":"Springer Science and Business Media LLC","issue":"13","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"EIPHI Graduate School","award":["NR-17-EURE-0002"],"award-info":[{"award-number":["NR-17-EURE-0002"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1007\/s10489-025-06823-5","type":"journal-article","created":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T13:58:31Z","timestamp":1756216711000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Survey on Tabular Data Privacy and Synthetic Data Generation in Industry 4.0"],"prefix":"10.1007","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4231-7829","authenticated-orcid":false,"given":"Hadi","family":"Koubeissy","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1644-3995","authenticated-orcid":false,"given":"Amir","family":"Amine","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marc","family":"Kamradt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0485-097X","authenticated-orcid":false,"given":"Abdallah","family":"Makhoul","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,8,26]]},"reference":[{"key":"6823_CR1","unstructured":"Schuh G, Anderl R, Gausemeier J, Ten\u00a0Hompel M, Wahlster W (2017) Industry 4.0 maturity index: shaping the digital transformation of companies (Herbert Utz Verlag)"},{"key":"6823_CR2","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/j.arcontrol.2010.02.008","volume":"34","author":"D Zuehlke","year":"2010","unstructured":"Zuehlke D (2010) Smartfactory-towards a factory-of-things. Annu. Rev. Control. 34:129\u2013138","journal-title":"Annu. Rev. Control."},{"key":"6823_CR3","unstructured":"Commission E et\u00a0al (2021) Industry 5.0\u2013 Towards a sustainable, human-centric and resilient European industry (Publications Office of the European Union)"},{"key":"6823_CR4","doi-asserted-by":"publisher","first-page":"530","DOI":"10.1016\/j.jmsy.2021.10.006","volume":"61","author":"X Xu","year":"2021","unstructured":"Xu X, Lu Y, Vogel-Heuser B, Wang L (2021) Industry 4.0 and industry 5.0-inception, conception and perception. J. Manuf. Syst. 61:530\u2013535","journal-title":"J. Manuf. Syst."},{"key":"6823_CR5","first-page":"4898","volume":"45","author":"S Sajid","year":"2021","unstructured":"Sajid S et al (2021) Data science applications for predictive maintenance and materials science in context to industry 4.0. Materials today: proceedings 45:4898\u20134905","journal-title":"Materials today: proceedings"},{"key":"6823_CR6","unstructured":"Makkar S, Devi GNR, Solanki VK, Gunjan VK, Garcia\u00a0Diaz V, Cardona M, Solanki VK, Sunitha KVN (2020) Applications of machine learning techniques in supply chain optimization. (eds Gunjan, V.\u00a0K., Garcia\u00a0Diaz, V., Cardona, M., Solanki, V.\u00a0K. & Sunitha, K. V.\u00a0N.) ICICCT 2019\u2013 System Reliability, Quality Control, Safety, Maintenance and Management, 861\u2013869 (Springer Singapore, Singapore)"},{"key":"6823_CR7","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.inffus.2021.11.011","volume":"81","author":"R Shwartz-Ziv","year":"2022","unstructured":"Shwartz-Ziv R, Armon A (2022) Tabular data: Deep learning is not all you need. Information Fusion 81:84\u201390","journal-title":"Information Fusion"},{"key":"6823_CR8","doi-asserted-by":"crossref","unstructured":"Onik MMH, Kim C-S, Yang J (2019) Personal data privacy challenges of the fourth industrial revolution","DOI":"10.23919\/ICACT.2019.8701932"},{"key":"6823_CR9","doi-asserted-by":"publisher","first-page":"6326","DOI":"10.1109\/TII.2022.3164741","volume":"18","author":"M Alazab","year":"2022","unstructured":"Alazab M, Gadekallu TR, Su C (2022) Guest editorial: Security and privacy issues in industry 4.0 applications. IEEE Trans. Industr. Inf. 18:6326\u20136329","journal-title":"IEEE Trans. Industr. Inf."},{"key":"6823_CR10","doi-asserted-by":"crossref","unstructured":"Sukhobok D, Nikolov N, Roman D (2017) Tabular data anomaly patterns","DOI":"10.1109\/Innovate-Data.2017.10"},{"key":"6823_CR11","doi-asserted-by":"publisher","first-page":"3278","DOI":"10.3390\/math11153278","volume":"11","author":"E Espinosa","year":"2023","unstructured":"Espinosa E, Figueira A (2023) On the quality of synthetic generated tabular data. Mathematics 11:3278","journal-title":"Mathematics"},{"key":"6823_CR12","unstructured":"Das HP et\u00a0al (2022) Conditional synthetic data generation for robust machine learning applications with limited pandemic data"},{"key":"6823_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.112223","volume":"166","author":"AX Wang","year":"2024","unstructured":"Wang AX, Chukova SS, Simpson CR, Nguyen BP (2024) Challenges and opportunities of generative models on tabular data. Appl. Soft Comput. 166:112223","journal-title":"Appl. Soft Comput."},{"key":"6823_CR14","doi-asserted-by":"publisher","first-page":"2195","DOI":"10.1007\/s11263-023-01966-9","volume":"132","author":"C Abou Akar","year":"2024","unstructured":"Abou Akar C et al (2024) Generative adversarial network applications in industry 4.0: A review. Int. J. Comput. Vision 132:2195\u20132254","journal-title":"Int. J. Comput. Vision"},{"key":"6823_CR15","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1214\/24-STS927","volume":"39","author":"J Drechsler","year":"2024","unstructured":"Drechsler J, Haensch A-C (2024) 30 Years of Synthetic Data. Stat. Sci. 39:221\u2013242. https:\/\/doi.org\/10.1214\/24-STS927","journal-title":"Stat. Sci."},{"key":"6823_CR16","doi-asserted-by":"publisher","first-page":"2015","DOI":"10.1177\/01423312221142564","volume":"45","author":"S Guan","year":"2023","unstructured":"Guan S et al (2023) Feedback-aided pd-type iterative learning control for time-varying systems with non-uniform trial lengths. Trans. Inst. Meas. Control. 45:2015\u20132026. https:\/\/doi.org\/10.1177\/01423312221142564","journal-title":"Trans. Inst. Meas. Control."},{"key":"6823_CR17","doi-asserted-by":"publisher","first-page":"1943","DOI":"10.1177\/01423312231225782","volume":"46","author":"Y Tao","year":"2024","unstructured":"Tao Y, Tao H, Zhuang Z, Stojanovic V, Paszke W (2024) Quantized iterative learning control of communication-constrained systems with encoding and decoding mechanism. Trans. Inst. Meas. Control. 46:1943\u20131954. https:\/\/doi.org\/10.1177\/01423312231225782","journal-title":"Trans. Inst. Meas. Control."},{"key":"6823_CR18","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6501\/ad0f6d","volume":"35","author":"H Tao","year":"2023","unstructured":"Tao H, Shi H, Qiu J, Jin G, Stojanovic V (2023) Planetary gearbox fault diagnosis based on fdknn-dgat with few labeled data. Meas. Sci. Technol. 35:025036. https:\/\/doi.org\/10.1088\/1361-6501\/ad0f6d","journal-title":"Meas. Sci. Technol."},{"key":"6823_CR19","doi-asserted-by":"crossref","unstructured":"Buggineni V, Chen C, Camelio J (2024) Enhancing manufacturing operations with synthetic data: a systematic framework for data generation, accuracy, and utility. Frontiers in Manufacturing Technology Volume 4 - 2024. https:\/\/www.frontiersin.org\/journals\/manufacturing-technology\/articles\/10.3389\/fmtec.2024.1320166","DOI":"10.3389\/fmtec.2024.1320166"},{"key":"6823_CR20","doi-asserted-by":"crossref","unstructured":"Figueira A, Vaz B (2022) Survey on synthetic data generation, evaluation methods and gans. Mathematics 10. https:\/\/www.mdpi.com\/2227-7390\/10\/15\/2733","DOI":"10.3390\/math10152733"},{"key":"6823_CR21","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1186\/s40537-023-00792-7","volume":"10","author":"J Fonseca","year":"2023","unstructured":"Fonseca J, Bacao F (2023) Tabular and latent space synthetic data generation: a literature review. Journal of Big Data 10:115","journal-title":"Journal of Big Data"},{"key":"6823_CR22","doi-asserted-by":"publisher","first-page":"7499","DOI":"10.1109\/TNNLS.2022.3229161","volume":"35","author":"V Borisov","year":"2024","unstructured":"Borisov V et al (2024) Deep neural networks and tabular data: A survey. IEEE Transactions on Neural Networks and Learning Systems 35:7499\u20137519","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"6823_CR23","doi-asserted-by":"crossref","unstructured":"Bourou S, El\u00a0Saer A, Velivassaki T-H, Voulkidis A, Zahariadis T (2021) A review of tabular data synthesis using gans on an ids dataset. Information 12. https:\/\/www.mdpi.com\/2078-2489\/12\/9\/375","DOI":"10.3390\/info12090375"},{"key":"6823_CR24","doi-asserted-by":"crossref","unstructured":"Hernandez M, Epelde G, Alberdi A, Cilla R, Rankin D (2022) Synthetic data generation for tabular health records: A systematic review. Neurocomputing 493:28\u201345. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0925231222004349","DOI":"10.1016\/j.neucom.2022.04.053"},{"key":"6823_CR25","doi-asserted-by":"crossref","unstructured":"Pezoulas VC et\u00a0al (2024) Synthetic data generation methods in healthcare: A review on open-source tools and methods. Computational and Structural Biotechnology Journal 23:2892\u20132910. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S2001037024002393","DOI":"10.1016\/j.csbj.2024.07.005"},{"key":"6823_CR26","doi-asserted-by":"publisher","first-page":"135392","DOI":"10.1109\/ACCESS.2021.3116481","volume":"9","author":"M Sahakyan","year":"2021","unstructured":"Sahakyan M, Aung Z, Rahwan T (2021) Explainable artificial intelligence for tabular data: A survey. IEEE Access 9:135392\u2013135422","journal-title":"IEEE Access"},{"key":"6823_CR27","volume-title":"& Hlupi\u0107, N","author":"FK Do\u0161ilovi\u0107","year":"2018","unstructured":"Do\u0161ilovi\u0107 FK, Br\u010di\u0107 M (2018) & Hlupi\u0107, N. A survey, Explainable artificial intelligence"},{"key":"6823_CR28","unstructured":"Fang X et\u00a0al (2024) Large language models (LLMs) on tabular data: Prediction, generation, and understanding - a survey. Transactions on Machine Learning Research. https:\/\/openreview.net\/forum?id=IZnrCGF9WI"},{"key":"6823_CR29","doi-asserted-by":"crossref","unstructured":"Yin P, Neubig G, Yih W-t, Riedel S, Jurafsky D, Chai J, Schluter N, Tetreault J (2020) TaBERT: Pretraining for joint understanding of textual and tabular data. (eds Jurafsky, D., Chai, J., Schluter, N. & Tetreault, J.) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 8413\u20138426 (Association for Computational Linguistics, Online). https:\/\/aclanthology.org\/2020.acl-main.745\/","DOI":"10.18653\/v1\/2020.acl-main.745"},{"key":"6823_CR30","doi-asserted-by":"crossref","unstructured":"Herzig J, Nowak PK, M\u00fcller T, Piccinno F, Eisenschlos J, Jurafsky D, Chai J, Schluter N, Tetreault J (2020) TaPas: Weakly supervised table parsing via pre-training. (eds Jurafsky, D., Chai, J., Schluter, N. & Tetreault, J.) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 4320\u20134333 (Association for Computational Linguistics, Online). https:\/\/aclanthology.org\/2020.acl-main.398\/","DOI":"10.18653\/v1\/2020.acl-main.398"},{"key":"6823_CR31","unstructured":"Bayat R (2023) A study on sample diversity in generative models: GANs vs. diffusion models. https:\/\/openreview.net\/forum?id=BQpCuJoMykZ"},{"key":"6823_CR32","doi-asserted-by":"crossref","unstructured":"Lautrup AD, Hyrup T, Zimek A, Schneider-Kamp P (2024) Systematic review of generative modelling tools and utility metrics for fully synthetic tabular data. ACM Comput. Surv. 57. https:\/\/doi.org\/10.1145\/3704437","DOI":"10.1145\/3704437"},{"key":"6823_CR33","volume-title":"Principles of copula theory","author":"F Durante","year":"2016","unstructured":"Durante F, Sempi C et al (2016) Principles of copula theory, vol 474. CRC Press Boca Raton, FL"},{"key":"6823_CR34","doi-asserted-by":"crossref","unstructured":"Aas K, Czado C, Frigessi A, Bakken H (2009) Pair-copula constructions of multiple dependence. Insurance: Mathematics and Economics 44:182\u2013198","DOI":"10.1016\/j.insmatheco.2007.02.001"},{"key":"6823_CR35","unstructured":"Chang K, Elidan G, Wu Y, Zhang Z, Koller D (2019) Vine copulas with monotone search for mixed data"},{"key":"6823_CR36","unstructured":"Elidan G Lafferty J, Williams C, Shawe-Taylor J, Zemel R, Culotta A (2010) Copula bayesian networks. (eds Lafferty, J., Williams, C., Shawe-Taylor, J., Zemel, R. & Culotta, A.) Advances in Neural Information Processing Systems, Vol.\u00a023 (Curran Associates, Inc.). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2010\/file\/2a79ea27c279e471f4d180b08d62b00a-Paper.pdf"},{"key":"6823_CR37","unstructured":"Kamthe S, Assefa S, Deisenroth M (2021) Copula flows for synthetic data generation. arXiv:2101.00598"},{"key":"6823_CR38","doi-asserted-by":"crossref","unstructured":"Goodfellow I et\u00a0al (2020) Generative adversarial networks. Commun. ACM 63, 139\u2013144. https:\/\/doi.org\/10.1145\/3422622","DOI":"10.1145\/3422622"},{"key":"6823_CR39","unstructured":"Arjovsky M, Chintala S, Bottou L, Precup D, Teh YW (2017) Wasserstein generative adversarial networks. (eds Precup, D. & Teh, Y.\u00a0W.) Proceedings of the 34th International Conference on Machine Learning, Vol.\u00a070 of Proceedings of Machine Learning Research, 214\u2013223 (PMLR). https:\/\/proceedings.mlr.press\/v70\/arjovsky17a.html"},{"key":"6823_CR40","unstructured":"Mirza M, Osindero S (2014) Conditional generative adversarial nets. arXiv:1411.1784"},{"key":"6823_CR41","unstructured":"Radford A, Metz L, Chintala S (2015) Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv:1511.06434"},{"key":"6823_CR42","doi-asserted-by":"publisher","unstructured":"Park N et\u00a0al (2018) Data synthesis based on generative adversarial networks. Proc. VLDB Endow. 11, 1071\u20131083. https:\/\/doi.org\/10.14778\/3231751.3231757","DOI":"10.14778\/3231751.3231757"},{"key":"6823_CR43","unstructured":"Xu L, Veeramachaneni K (2018) Synthesizing tabular data using generative adversarial networks. arXiv:1811.11264"},{"key":"6823_CR44","unstructured":"Xu L, Skoularidou M, Cuesta-Infante A, Veeramachaneni K (2019) Modeling tabular data using conditional gan"},{"key":"6823_CR45","unstructured":"Uci machine learning repository. https:\/\/archive.ics.uci.edu\/. Accessed: 2024-07-14"},{"key":"6823_CR46","unstructured":"Zhao Z, Kunar A, Birke R, Chen LY (2021) Balasubramanian, V.\u00a0N. & Tsang, I. (eds) Ctab-gan: Effective table data synthesizing. (eds Balasubramanian, V.\u00a0N. & Tsang, I.) Proceedings of The 13th Asian Conference on Machine Learning, Vol. 157 of Proceedings of Machine Learning Research, 97\u2013112 (PMLR). https:\/\/proceedings.mlr.press\/v157\/zhao21a.html"},{"key":"6823_CR47","doi-asserted-by":"publisher","first-page":"1296508","DOI":"10.3389\/fdata.2023.1296508","volume":"6","author":"Z Zhao","year":"2024","unstructured":"Zhao Z, Kunar A, Birke R, Van der Scheer H, Chen LY (2024) Ctab-gan+: Enhancing tabular data synthesis. Frontiers in big Data 6:1296508","journal-title":"Frontiers in big Data"},{"key":"6823_CR48","unstructured":"Wen B, Cao Y, Yang F, Subbalakshmi K, Chandramouli R (2022) Causal-TGAN: Modeling tabular data using causally-aware GAN. https:\/\/openreview.net\/forum?id=BEhxCh4dvW5"},{"key":"6823_CR49","unstructured":"Ho J, Jain A, Abbeel P, Larochelle H, Ranzato M, Hadsell R, Balcan M, Lin H (2020) Denoising diffusion probabilistic models. (eds Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M. & Lin, H.) Advances in Neural Information Processing Systems, Vol.\u00a033, 6840\u20136851 (Curran Associates, Inc.). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/4c5bcfec8584af0d967f1ab10179ca4b-Paper.pdf"},{"key":"6823_CR50","unstructured":"Sohl-Dickstein J, Weiss E, Maheswaranathan N, Ganguli S, Bach F, Blei D (2015) Deep unsupervised learning using nonequilibrium thermodynamics. (eds Bach, F. & Blei, D.) Proceedings of the 32nd International Conference on Machine Learning, Vol.\u00a037 of Proceedings of Machine Learning Research, 2256\u20132265 (PMLR, Lille, France). https:\/\/proceedings.mlr.press\/v37\/sohl-dickstein15.html"},{"key":"6823_CR51","unstructured":"Kotelnikov A, Baranchuk D, Rubachev I, Babenko A (2023) Tabddpm: modelling tabular data with diffusion models"},{"key":"6823_CR52","unstructured":"Pyrcz MJ, Deutsch CV, Deutsch J (2018) Transforming data to a gaussian distribution. Geostatistics Lessons"},{"key":"6823_CR53","unstructured":"Gorishniy Y, Rubachev I, Khrulkov V, Babenko A, Ranzato M, Beygelzimer A, Dauphin Y, Liang P, Vaughan JW (2021) Revisiting deep learning models for tabular data. (eds Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P. & Vaughan, J.\u00a0W.) Advances in Neural Information Processing Systems, Vol.\u00a034, 18932\u201318943 (Curran Associates, Inc.). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/9d86d83f925f2149e9edb0ac3b49229c-Paper.pdf"},{"key":"6823_CR54","doi-asserted-by":"crossref","unstructured":"Villaiz\u00e1n-Vallelado M, Salvatori M, Segura\u00a0Perales C, Arapakis I (2025) Diffusion models for tabular data imputation and synthetic data generation. ACM Trans. Knowl. Discov. Data. https:\/\/doi.org\/10.1145\/3742435. Just Accepted","DOI":"10.1145\/3742435"},{"key":"6823_CR55","unstructured":"Achiam J et\u00a0al (2023) Gpt-4 technical report. arXiv:2303.08774"},{"key":"6823_CR56","unstructured":"Vaswani A et\u00a0al. Guyon, I. et\u00a0al. (eds) Attention is all you need. (eds Guyon, I. et\u00a0al.) Advances in Neural Information Processing Systems, Vol.\u00a030 (Curran Associates, Inc., 2017). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"6823_CR57","unstructured":"Minaee S et\u00a0al (2024) Large language models: A survey. arXiv:2402.06196"},{"key":"6823_CR58","unstructured":"Zhao WX et\u00a0al (2023) A survey of large language models. arXiv:2303.18223"},{"key":"6823_CR59","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K, Burstein J, Doran C, Solorio T (2019) BERT: Pre-training of deep bidirectional transformers for language understanding. (eds Burstein, J., Doran, C. & Solorio, T.) Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), 4171\u20134186 (Association for Computational Linguistics, Minneapolis, Minnesota. https:\/\/aclanthology.org\/N19-1423\/"},{"key":"6823_CR60","unstructured":"Radford A, Narasimhan K, Salimans T, Sutskever I et\u00a0al (2018) Improving language understanding by generative pre-training"},{"key":"6823_CR61","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford A et al (2019) Language models are unsupervised multitask learners. OpenAI blog 1:9","journal-title":"OpenAI blog"},{"key":"6823_CR62","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel C et al (2020) Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21:1\u201367","journal-title":"J. Mach. Learn. Res."},{"key":"6823_CR63","doi-asserted-by":"crossref","unstructured":"Lewis M et\u00a0al (2020) Jurafsky, D., Chai, J., Schluter, N. & Tetreault, J. (eds) BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. (eds Jurafsky, D., Chai, J., Schluter, N. & Tetreault, J.) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 7871\u20137880 (Association for Computational Linguistics, Online). https:\/\/aclanthology.org\/2020.acl-main.703\/","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"6823_CR64","unstructured":"Borisov V, Sessler K, Leemann T, Pawelczyk M, Kasneci G (2023) Language models are realistic tabular data generators. https:\/\/openreview.net\/forum?id=cEygmQNOeI"},{"key":"6823_CR65","doi-asserted-by":"publisher","unstructured":"Becker B, Kohavi R (1996) Adult. UCI Machine Learning Repository. DOI: https:\/\/doi.org\/10.24432\/C5XW20","DOI":"10.24432\/C5XW20"},{"key":"6823_CR66","doi-asserted-by":"crossref","unstructured":"Wallace E, Wang Y, Li S, Singh S, Gardner M, Inui K, Jiang J, Ng V, Wan X (2019) Do NLP models know numbers? probing numeracy in embeddings. (eds Inui, K., Jiang, J., Ng, V. & Wan, X.) Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 5307\u20135315 (Association for Computational Linguistics, Hong Kong, China). https:\/\/aclanthology.org\/D19-1534\/","DOI":"10.18653\/v1\/D19-1534"},{"key":"6823_CR67","unstructured":"Brown TB et\u00a0al (2020) Language models are few-shot learners"},{"key":"6823_CR68","unstructured":"Kaggle (2024) Kaggle: Your machine learning and data science community. https:\/\/www.kaggle.com\/. Accessed: 2024-07-14"},{"key":"6823_CR69","unstructured":"Sanh V, Debut L, Chaumond J, Wolf T (2019) Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. arXiv:1910.01108"},{"key":"6823_CR70","unstructured":"Bellman R, Bellman R, Corporation R (1957) Dynamic Programming Rand Corporation research study (Princeton University Press). https:\/\/books.google.de\/books?id=rZW4ugAACAAJ"},{"key":"6823_CR71","unstructured":"Zhao Z, Birke R, Chen LY (2023) Tabula: Harnessing language models for tabular data synthesis. CoRR abs\/2310.12746. https:\/\/doi.org\/10.48550\/arXiv.2310.12746"},{"key":"6823_CR72","doi-asserted-by":"publisher","first-page":"177460","DOI":"10.1109\/ACCESS.2019.2958284","volume":"7","author":"\u00c1LP G\u00f3mez","year":"2019","unstructured":"G\u00f3mez \u00c1LP et al (2019) On the generation of anomaly detection datasets in industrial control systems. IEEE Access 7:177460\u2013177473","journal-title":"IEEE Access"},{"key":"6823_CR73","volume-title":"& Ma, J","author":"T Xiao","year":"2018","unstructured":"Xiao T, Hong J (2018) & Ma, J. Exchanging latent encodings with gan for transferring multiple face attributes, Elegant"},{"key":"6823_CR74","unstructured":"Kharoua RE (2024) Predicting manufacturing defects dataset. https:\/\/www.kaggle.com\/datasets\/rabieelkharoua\/predicting-manufacturing-defects-dataset\/data. Accessed: 2024-12-17"},{"key":"6823_CR75","doi-asserted-by":"publisher","unstructured":"AI4I 2020 Predictive Maintenance Dataset (2020) UCI Machine Learning Repository. https:\/\/doi.org\/10.24432\/C5HS5C","DOI":"10.24432\/C5HS5C"},{"key":"6823_CR76","doi-asserted-by":"publisher","unstructured":"Ferreira R, Martiniano A, Ferreira A, Ferreira A, Sassi R (2016) Daily Demand Forecasting Orders. UCI Machine Learning Repository. https:\/\/doi.org\/10.24432\/C5BC8T","DOI":"10.24432\/C5BC8T"},{"key":"6823_CR77","doi-asserted-by":"publisher","unstructured":"Yeh I-C (1998) Concrete Compressive Strength. UCI Machine Learning Repository. https:\/\/doi.org\/10.24432\/C5PK67","DOI":"10.24432\/C5PK67"},{"key":"6823_CR78","doi-asserted-by":"publisher","unstructured":"Hamidieh K (2018) Superconductivty Data. UCI Machine Learning Repository. https:\/\/doi.org\/10.24432\/C53P47","DOI":"10.24432\/C53P47"},{"key":"6823_CR79","doi-asserted-by":"publisher","unstructured":"Nash W, Sellers T, Talbot S, Cawthorn A, Ford W (1995) Abalone. UCI Machine Learning Repository. https:\/\/doi.org\/10.24432\/C55C7W","DOI":"10.24432\/C55C7W"},{"key":"6823_CR80","doi-asserted-by":"publisher","unstructured":"Blackard J (1998) Covertype. UCI Machine Learning Repository. https:\/\/doi.org\/10.24432\/C50K5N","DOI":"10.24432\/C50K5N"},{"key":"6823_CR81","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1023\/A:1007421730016","volume":"29","author":"J Binder","year":"1997","unstructured":"Binder J, Koller D, Russell S, Kanazawa K (1997) Adaptive probabilistic networks with hidden variables. Mach. Learn. 29:213\u2013244","journal-title":"Mach. Learn."},{"key":"6823_CR82","unstructured":"Adam WK (2016) Expedia hotel recommendations. https:\/\/kaggle.com\/competitions\/expedia-hotel-recommendations"},{"key":"6823_CR83","doi-asserted-by":"publisher","unstructured":"Singh K (2015) Facebook Comment Volume. UCI Machine Learning Repository. https:\/\/doi.org\/10.24432\/C5Q886","DOI":"10.24432\/C5Q886"},{"key":"6823_CR84","doi-asserted-by":"publisher","unstructured":"Stolfo S, Fan W, Lee W, Prodromidis A, Chan P (1999) KDD Cup 1999 Data. UCI Machine Learning Repository. https:\/\/doi.org\/10.24432\/C51C7N","DOI":"10.24432\/C51C7N"},{"key":"6823_CR85","doi-asserted-by":"publisher","first-page":"11147","DOI":"10.1109\/ACCESS.2022.3144765","volume":"10","author":"FK Dankar","year":"2022","unstructured":"Dankar FK, Ibrahim MK, Ismail L (2022) A multi-dimensional evaluation of synthetic data generators. IEEE Access 10:11147\u201311158","journal-title":"IEEE Access"},{"key":"6823_CR86","doi-asserted-by":"publisher","first-page":"11147","DOI":"10.1109\/ACCESS.2022.3144765","volume":"10","author":"FK Dankar","year":"2022","unstructured":"Dankar FK, Ibrahim MK, Ismail L (2022) A multi-dimensional evaluation of synthetic data generators. IEEE Access 10:11147\u201311158","journal-title":"IEEE Access"},{"key":"6823_CR87","doi-asserted-by":"crossref","unstructured":"Liu Q, Khalil M, Jovanovic J, Shakya R (2024) Scaling while privacy preserving: A comprehensive synthetic tabular data generation and evaluation in learning analytics. https:\/\/doi.org\/10.1145\/3636555.3636921","DOI":"10.1145\/3636555.3636921"},{"key":"6823_CR88","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12874-020-00977-1","volume":"20","author":"A Goncalves","year":"2020","unstructured":"Goncalves A et al (2020) Generation and evaluation of synthetic patient data. BMC Med. Res. Methodol. 20:1\u201340","journal-title":"BMC Med. Res. Methodol."},{"key":"6823_CR89","unstructured":"Tiwald P, Ebert A, Soukup DT (2021) Representative & fair synthetic data. CoRR abs\/2104.03007. https:\/\/arxiv.org\/abs\/2104.03007"},{"key":"6823_CR90","unstructured":"Arora S, Ge R, Liang Y, Ma T, Zhang Y (2017) Generalization and equilibrium in generative adversarial nets (gans)"},{"key":"6823_CR91","unstructured":"Tao L, Xu S, Wang C-H, Suh N, Cheng G (2024) Discriminative estimation of total variation distance: A fidelity auditor for generative data. arXiv:2405.15337"},{"key":"6823_CR92","doi-asserted-by":"crossref","unstructured":"Dandekar A, Zen RA, Bressan S (2017) Comparative evaluation of synthetic data generation methods","DOI":"10.1007\/978-3-319-98812-2_35"},{"key":"6823_CR93","doi-asserted-by":"publisher","unstructured":"Ma T (2018) Generalization and equilibrium in generative adversarial nets (gans) (invited talk). https:\/\/doi.org\/10.1145\/3188745.3232194","DOI":"10.1145\/3188745.3232194"},{"key":"6823_CR94","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1166-2","volume-title":"Asymptotics in statistics: some basic concepts","author":"LM Le Cam","year":"2000","unstructured":"Le Cam LM, Yang GL (2000) Asymptotics in statistics: some basic concepts. Springer Science & Business Media, Berlin"},{"key":"6823_CR95","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1007\/s41468-017-0008-7","volume":"1","author":"A Robinson","year":"2017","unstructured":"Robinson A, Turner K (2017) Hypothesis testing for topological data analysis. Journal of Applied and Computational Topology 1:241\u2013261. https:\/\/doi.org\/10.1007\/s41468-017-0008-7","journal-title":"Journal of Applied and Computational Topology"},{"key":"6823_CR96","unstructured":"Khrulkov V, Oseledets I (2018) Geometry score: A method for comparing generative adversarial networks"},{"key":"6823_CR97","doi-asserted-by":"publisher","unstructured":"Ping H, Stoyanovich J, Howe B (2017) Datasynthesizer: Privacy-preserving synthetic datasets. https:\/\/doi.org\/10.1145\/3085504.3091117","DOI":"10.1145\/3085504.3091117"},{"key":"6823_CR98","doi-asserted-by":"crossref","unstructured":"Yale A et\u00a0al (2020) Synthesizing Quality Open Data Assets from Private Health Research Studies. https:\/\/inria.hal.science\/hal-03158556","DOI":"10.1007\/978-3-030-61146-0_26"},{"key":"6823_CR99","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1007\/s10618-024-01081-4","volume":"39","author":"AD Lautrup","year":"2024","unstructured":"Lautrup AD, Hyrup T, Zimek A, Schneider-Kamp P (2024) Syntheval: a framework for detailed utility and privacy evaluation of tabular synthetic data. Data Min. Knowl. Disc. 39:6. https:\/\/doi.org\/10.1007\/s10618-024-01081-4","journal-title":"Data Min. Knowl. Disc."},{"key":"6823_CR100","doi-asserted-by":"crossref","unstructured":"Yale A et\u00a0al (2019) Privacy preserving synthetic health data","DOI":"10.1016\/j.neucom.2019.12.136"},{"key":"6823_CR101","doi-asserted-by":"publisher","first-page":"6395","DOI":"10.3390\/app12136395","volume":"12","author":"I Ogrezeanu","year":"2022","unstructured":"Ogrezeanu I et al (2022) Privacy-preserving and explainable ai in industrial applications. Appl. Sci. 12:6395","journal-title":"Appl. Sci."},{"key":"6823_CR102","unstructured":"Elliot M (2015) Final report on the disclosure risk associated with the synthetic data produced by the sylls team. Report 2015 2"},{"key":"6823_CR103","doi-asserted-by":"crossref","unstructured":"Taub, J., Elliot, M., Pampaka, M. & Smith, D. Differential correct attribution probability for synthetic data: an exploration (2018)","DOI":"10.1007\/978-3-319-99771-1_9"},{"key":"6823_CR104","doi-asserted-by":"crossref","unstructured":"Hittmeir M, Mayer R, Ekelhart A (2020) A baseline for attribute disclosure risk in synthetic data","DOI":"10.1145\/3374664.3375722"},{"key":"6823_CR105","doi-asserted-by":"publisher","unstructured":"Park N et\u00a0al (2018) Data synthesis based on generative adversarial networks. Proc. VLDB Endow. 11, 1071\u20131083. https:\/\/doi.org\/10.14778\/3231751.3231757","DOI":"10.14778\/3231751.3231757"},{"key":"6823_CR106","doi-asserted-by":"crossref","unstructured":"Sivakumar J, Ramamurthy K, Radhakrishnan M, Won D (2023) Generativemtd: A deep synthetic data generation framework for small datasets. Knowledge-Based Systems 280, 110956. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0950705123007062","DOI":"10.1016\/j.knosys.2023.110956"},{"key":"6823_CR107","doi-asserted-by":"crossref","unstructured":"Rashidian S et\u00a0al (2020) Michalowski, M. & Moskovitch, R. (eds) Smooth-gan: Towards sharp and smooth synthetic ehr data generation. (eds Michalowski, M. & Moskovitch, R.) Artificial Intelligence in Medicine, 37\u201348 (Springer International Publishing, Cham)","DOI":"10.1007\/978-3-030-59137-3_4"},{"key":"6823_CR108","doi-asserted-by":"crossref","unstructured":"Norgaard S, Saeedi R, Sasani K, Gebremedhin AH (2018) Synthetic sensor data generation for health applications: A supervised deep learning approach","DOI":"10.1109\/EMBC.2018.8512470"},{"key":"6823_CR109","doi-asserted-by":"publisher","first-page":"663","DOI":"10.1111\/rssa.12358","volume":"181","author":"J Snoke","year":"2018","unstructured":"Snoke J, Raab GM, Nowok B, Dibben C, Slavkovic A (2018) General and Specific Utility Measures for Synthetic Data. J. R. Stat. Soc. Ser. A Stat. Soc. 181:663\u2013688. https:\/\/doi.org\/10.1111\/rssa.12358","journal-title":"J. R. Stat. Soc. Ser. A Stat. Soc."},{"key":"6823_CR110","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1109\/TAI.2022.3229289","volume":"5","author":"VS Chundawat","year":"2022","unstructured":"Chundawat VS, Tarun AK, Mandal M, Lahoti M, Narang P (2022) A universal metric for robust evaluation of synthetic tabular data. IEEE Transactions on Artificial Intelligence 5:300\u2013309","journal-title":"IEEE Transactions on Artificial Intelligence"},{"key":"6823_CR111","unstructured":"Alaa A, Van\u00a0Breugel B, Saveliev ES, van\u00a0der Schaar M (2022) How faithful is your synthetic data? sample-level metrics for evaluating and auditing generative models"},{"key":"6823_CR112","doi-asserted-by":"publisher","first-page":"15795","DOI":"10.1109\/ACCESS.2025.3532128","volume":"13","author":"A Kiran","year":"2025","unstructured":"Kiran A, Rubini P, Kumar SS (2025) Comprehensive review of privacy, utility, and fairness offered by synthetic data. IEEE Access 13:15795\u201315811","journal-title":"IEEE Access"},{"key":"6823_CR113","unstructured":"Kwatra S, Torra V, Bieker F, de\u00a0Conca S, Gruschka N, Jensen M, Schiering I (2024) Empirical evaluation of synthetic data created by generative models via attribute inference attack. (eds Bieker, F., de\u00a0Conca, S., Gruschka, N., Jensen, M. & Schiering, I.) Privacy and Identity Management. Sharing in a Digital World, 282\u2013291 (Springer Nature Switzerland, Cham)"},{"key":"6823_CR114","doi-asserted-by":"publisher","unstructured":"Liu Q et\u00a0al (2025) Can synthetic data be fair and private? a comparative study of synthetic data generation and fairness algorithms. https:\/\/doi.org\/10.1145\/3706468.3706546","DOI":"10.1145\/3706468.3706546"},{"key":"6823_CR115","unstructured":"Li Z et\u00a0al (2025) Diffusion models for tabular data: Challenges, current progress, and future directions. arXiv:2502.17119"},{"key":"6823_CR116","unstructured":"Barr AA, Rozman R, Guo E (2025) Generative adversarial networks vs large language models: a comparative study on synthetic tabular data generation. arXiv:2502.14523"},{"key":"6823_CR117","doi-asserted-by":"crossref","unstructured":"Thakur R, Poonia RC (2025) Mathematical capabilities of llms","DOI":"10.1109\/ICCCIT62592.2025.10928013"},{"key":"6823_CR118","doi-asserted-by":"crossref","unstructured":"Schwartz E et\u00a0al (2024) Numerologic: Number encoding for enhanced llms\u2019 numerical reasoning. arXiv:2404.00459","DOI":"10.18653\/v1\/2024.emnlp-main.12"},{"key":"6823_CR119","unstructured":"Singh AK, Strouse D (2024) Tokenization counts: the impact of tokenization on arithmetic in frontier llms. arXiv:2402.14903"},{"key":"6823_CR120","first-page":"3","volume":"1","author":"EJ Hu","year":"2022","unstructured":"Hu EJ et al (2022) Lora: Low-rank adaptation of large language models. ICLR 1:3","journal-title":"ICLR"},{"key":"6823_CR121","first-page":"10088","volume":"36","author":"T Dettmers","year":"2023","unstructured":"Dettmers T, Pagnoni A, Holtzman A, Zettlemoyer L (2023) Qlora: Efficient finetuning of quantized llms. Adv. Neural. Inf. Process. Syst. 36:10088\u201310115","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6823_CR122","unstructured":"Wan Z et\u00a0al (2024) Efficient large language models: A survey. Transactions on Machine Learning Research. https:\/\/openreview.net\/forum?id=bsCCJHbO8A. Survey Certification"},{"key":"6823_CR123","unstructured":"Zhou Z et\u00a0al (2024) A survey on efficient inference for large language models. arXiv:2404.14294"},{"key":"6823_CR124","doi-asserted-by":"crossref","unstructured":"Li B, Jiang Y, Gadepally V, Tiwari D (2024) Llm inference serving: Survey of recent advances and opportunities. arXiv:2407.12391","DOI":"10.1109\/HPEC62836.2024.10938426"},{"key":"6823_CR125","unstructured":"Leviathan Y, Kalman M, Matias Y (2023) Fast inference from transformers via speculative decoding"},{"key":"6823_CR126","doi-asserted-by":"crossref","unstructured":"Assefa SA et\u00a0al (2021) Generating synthetic data in finance: opportunities, challenges and pitfalls. https:\/\/doi.org\/10.1145\/3383455.3422554","DOI":"10.2139\/ssrn.3634235"},{"key":"6823_CR127","first-page":"75","volume":"10","author":"K Kanagarla","year":"2024","unstructured":"Kanagarla K (2024) The role of synthetic data in ensuring data privacy and enabling secure analytics. European Journal of Engineering and Technology Research 10:75\u201379","journal-title":"European Journal of Engineering and Technology Research"},{"key":"6823_CR128","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1038\/s41746-023-00927-3","volume":"6","author":"M Giuffr\u00e8","year":"2023","unstructured":"Giuffr\u00e8 M, Shung DL (2023) Harnessing the power of synthetic data in healthcare: innovation, application, and privacy. Npj Digital Medicine 6:186. https:\/\/doi.org\/10.1038\/s41746-023-00927-3","journal-title":"Npj Digital Medicine"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06823-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-025-06823-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06823-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T14:33:24Z","timestamp":1758983604000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-025-06823-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":128,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["6823"],"URL":"https:\/\/doi.org\/10.1007\/s10489-025-06823-5","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]},"assertion":[{"value":"29 July 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 August 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Materials availability"}}],"article-number":"935"}}