{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T20:56:30Z","timestamp":1775163390824,"version":"3.50.1"},"reference-count":88,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["24JG0500302"],"award-info":[{"award-number":["24JG0500302"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62576178"],"award-info":[{"award-number":["62576178"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2433216"],"award-info":[{"award-number":["U2433216"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Fuzzy Syst."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tfuzz.2026.3665818","type":"journal-article","created":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T21:20:12Z","timestamp":1771622412000},"page":"1064-1078","source":"Crossref","is-referenced-by-count":0,"title":["Auditing Partial Dataset Usage in Large Language Models via Fuzzy Membership Aggregation"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0570-8626","authenticated-orcid":false,"given":"Hongyu","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6798-1118","authenticated-orcid":false,"given":"Sichu","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3241-6122","authenticated-orcid":false,"given":"Bofan","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8214-6809","authenticated-orcid":false,"given":"Shi-Lin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4183-3645","authenticated-orcid":false,"given":"Zhuosheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3180-7347","authenticated-orcid":false,"given":"Weiping","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Nantong University, Nantong, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"ChatGPT","year":"2025"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"key":"ref3","first-page":"22199","article-title":"Large language models are zero-shot reasoners","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Kojima","year":"2022"},{"key":"ref4","first-page":"75993","article-title":"On the planning abilities of large language models-a critical investigation","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Valmeekam","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-024-01959-9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-08866-7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06924-6"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06792-0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09215-4"},{"key":"ref10","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref11","first-page":"49523","article-title":"Position: Will we run out of data? Limits of LLM scaling based on human-generated data","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Villalobos","year":"2024"},{"key":"ref12","first-page":"11940","article-title":"DE-COP: Detecting copyrighted content in language models training data","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Duarte","year":"2024"},{"key":"ref13","first-page":"36670","article-title":"Fantastic copyrighted beasts and how (not) to generate them","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"He","year":"2025"},{"key":"ref14","first-page":"9182","article-title":"Measuring non-adversarial reproduction of training data in large language models","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Aerni","year":"2025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.810"},{"key":"ref16","first-page":"56589","article-title":"Proving test set contamination in black-box language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Oren","year":"2024"},{"key":"ref17","article-title":"ChatGPT\u2019s viral studio Ghiblistyle images highlight AI copyright concerns","year":"2025","journal-title":"AP News"},{"key":"ref18","article-title":"Meta got caught gaming AI benchmarks for Llama 4 maverick","author":"Wiggers","year":"2025","journal-title":"Verge"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"ref20","first-page":"50358","article-title":"Scaling data-constrained language models","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Muennighoff","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755002"},{"key":"ref22","first-page":"62476","article-title":"Catapults in SGD: Spikes in the training loss and their impact on generalization through feature learning","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Zhu","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.234"},{"key":"ref24","first-page":"1589","article-title":"Membership inference attacks against vision-language models","volume-title":"Proc. 34th USENIX Secur. Symp.","author":"Hu","year":"2025"},{"key":"ref25","first-page":"124069","article-title":"LLM dataset inference: Did you train on my dataset?","volume-title":"Proc. 38th Int. Conf. Neural Inf. Process. Syst.","author":"Maini","year":"2025"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CSF.2018.00027"},{"key":"ref27","first-page":"51318","article-title":"Detecting pretraining data from large language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Shi","year":"2024"},{"key":"ref28","article-title":"Do membership inference attacks work on large language models?","volume-title":"Proc. 1st Conf. Lang. Model.","author":"Duan","year":"2024"},{"key":"ref29","first-page":"2397","article-title":"Pythia: A suite for analyzing large language models across training and scaling","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Biderman","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/S0019-9958(65)90241-X"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/91.227383"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.bigscience-1.9"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.31003\/uspnf_m29160_01_02"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/SP61157.2025.00025"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3265535"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681610"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2371"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_26"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3690226"},{"key":"ref40","first-page":"11313","article-title":"Data taggants: Dataset ownership verification via harmless targeted data poisoning","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Bouaziz","year":"2025"},{"key":"ref41","first-page":"2222","article-title":"Dataset inference: Ownership resolution in machine learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Maini","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3155921"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3546223"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26771"},{"key":"ref45","article-title":"On the robustness of dataset inference","author":"Szyller","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/SaTML64287.2025.00025"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714703"},{"key":"ref48","first-page":"1249","article-title":"Evading data provenance in deep neural networks","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Zhu","year":"2025"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3233\/faia250907"},{"key":"ref50","first-page":"2633","article-title":"Extracting training data from large language models","volume-title":"Proc. 30th USENIX Secur. Symp. (USENIX Secur. 21)","author":"Carlini","year":"2021"},{"key":"ref51","first-page":"101298","article-title":"Min-k : Improved baseline for pre-training data detection from large language models","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Zhang","year":"2025"},{"key":"ref52","first-page":"33329","article-title":"How much of my dataset did you use? Quantitative data usage inference in machine learning","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Tong","year":"2025"},{"key":"ref53","first-page":"48713","article-title":"Data mixing laws: Optimizing data mixtures by predicting language modeling performance","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Ye","year":"2025"},{"key":"ref54","first-page":"89055","article-title":"Scalable extraction of training data from aligned, production language models","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Nasr","year":"2025"},{"key":"ref55","first-page":"14807","article-title":"DIS-CO: Discovering copyrighted content in VLMs training data","volume-title":"Proc. 42nd Int. Conf. Mach. Learn.","author":"Duarte","year":"2025"},{"key":"ref56","first-page":"18607","article-title":"Measuring forgetting of memorized training examples","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Jagielski","year":"2023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/34.3891"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.1993.390281"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/21.52551"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709393"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2025.3575060"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2019.2924396"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.1993.390282"},{"key":"ref64","article-title":"tiktoken"},{"key":"ref65","article-title":"The pile: An 800GB dataset of diverse text for language modeling","author":"Gao","year":"2020"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref67","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i18.34055"},{"key":"ref69","article-title":"Towards understanding ensemble, knowledge distillation and self-distillation in deep learning","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Allen-Zhu","year":"2023"},{"key":"ref70","first-page":"3351","article-title":"Self-distillation amplifies regularization in Hilbert space","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Mobahi","year":"2020"},{"key":"ref71","first-page":"1321","article-title":"On calibration of modern neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guo","year":"2017"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2659"},{"key":"ref73","first-page":"37396","article-title":"Robust automatic modulation classification with fuzzy regularization","volume-title":"Proc. 42nd Int. Conf. Mach. Learn.","author":"Liang","year":"2025"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/91.481845"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/91.531767"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/91.554449"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2021.3076265"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2024.3393710"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2024.3514853"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2018.2849736"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2025.3550749"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3484448"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1976.1055501"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3131"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref86","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Khosla","year":"2020"},{"key":"ref87","article-title":"Scalable extraction of training data from aligned, production language models","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Nasr","year":"2025"},{"key":"ref88","first-page":"40306","article-title":"Bag of tricks for training data extraction from language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu","year":"2023"}],"container-title":["IEEE Transactions on Fuzzy Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/91\/11466357\/11403983.pdf?arnumber=11403983","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:54:09Z","timestamp":1775159649000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11403983\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":88,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tfuzz.2026.3665818","relation":{},"ISSN":["1063-6706","1941-0034"],"issn-type":[{"value":"1063-6706","type":"print"},{"value":"1941-0034","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}