{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T10:43:39Z","timestamp":1777459419355,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,27]]},"DOI":"10.1145\/3805621.3807630","type":"proceedings-article","created":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T13:08:45Z","timestamp":1777381725000},"page":"139-146","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Peeling the Layers of Privacy-Utility Onion on Tabular Data"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2605-8071","authenticated-orcid":false,"given":"Jiawei","family":"Wang","sequence":"first","affiliation":[{"name":"University of Southampton, Southampton, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6549-3414","authenticated-orcid":false,"given":"Zilong","family":"Zhao","sequence":"additional","affiliation":[{"name":"Betterdata AI, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2886-8445","authenticated-orcid":false,"given":"Leonardo","family":"Aniello","sequence":"additional","affiliation":[{"name":"University of Southampton, Southampton, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8870-5694","authenticated-orcid":false,"given":"Han","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Southampton, Southampton, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3690194"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383455.3422554"},{"key":"e_1_3_2_1_4_1","unstructured":"Li Bai Qingqing Ye Xinwei Zhang Sen Zhang Zi Liang Jianliang Xu and Haibo Hu. 2025. Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_5_1","unstructured":"Barry Becker. 1996. Adult Data Set (Census Income). https:\/\/www.cs.toronto.edu\/~delve\/data\/adult\/adultDetail.html. Accessed 2026-02-21. Reports cleaned split: train=30162 test=15060 after removing unknowns."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","first-page":"314","DOI":"10.52202\/075280-0016","article-title":"Scalable membership inference attacks via quantile regression","volume":"36","author":"Bertran Martin","year":"2023","unstructured":"Martin Bertran, Shuai Tang, Aaron Roth, Michael Kearns, Jamie H Morgenstern, and Steven Z Wu. 2023. Scalable membership inference attacks via quantile regression. Advances in Neural Information Processing Systems 36 (2023), 314\u2013330.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_7_1","unstructured":"Jock Blackard. 1998. Covertype. https:\/\/archive.ics.uci.edu\/ml\/datasets\/covertype. Accessed 2026-02-21. Reports 581 012 instances and 7 classes."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00019"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP46214.2022.9833649"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0964"},{"key":"e_1_3_2_1_11_1","unstructured":"Nicholas Carlini Florian Tramer Eric Wallace Matthew Jagielski Ariel Herbert-Voss Katherine Lee Adam Roberts Tom Brown Dawn Song Ulfar Erlingsson et al. 2021. Extracting training data from large language models. In 30th USENIX security symposium (USENIX Security 21). 2633\u20132650."},{"key":"e_1_3_2_1_12_1","volume-title":"Tighter Privacy Auditing of DP-SGD. In International Conference on Learning Representations (ICLR).","author":"T. Cebere","year":"2025","unstructured":"T. Cebere et al. 2025. Tighter Privacy Auditing of DP-SGD. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_13_1","unstructured":"Chih-Chung Chang and Chih-Jen Lin. 2010. LIBSVM Data Sets. ALOI. https:\/\/www.csie.ntu.edu.tw\/~cjlin\/libsvmtools\/datasets\/multiclass.html. Accessed 2026-02-21. Reports ALOI has 108 000 instances and 1 000 classes."},{"key":"e_1_3_2_1_14_1","volume-title":"33rd USENIX Security Symposium (USENIX Security 24)","author":"Chang Hongyan","year":"2024","unstructured":"Hongyan Chang, Brandon Edwards, Anindya S Paul, and Reza Shokri. 2024. Efficient privacy auditing in federated learning. In 33rd USENIX Security Symposium (USENIX Security 24). 307\u2013323."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372297.3417238"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2024.23014"},{"key":"e_1_3_2_1_17_1","volume-title":"Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuning. In Neurips Safe Generative AI Workshop","author":"Roy Chowdhury Somnath Basu","year":"2024","unstructured":"Somnath Basu Roy Chowdhury, Krzysztof Marcin Choromanski, Arijit Se-hanobish, Kumar Avinava Dubey, and Snigdha Chaturvedi. [n. d.]. Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuning. In Neurips Safe Generative AI Workshop 2024."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357713.3384290"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1882471.1882479"},{"key":"e_1_3_2_1_20_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Georgiev Kristian","year":"2025","unstructured":"Kristian Georgiev, Roy Rinberg, Sung Min Park, Shivam Garg, Andrew Ilyas, Aleksander Madry, and Seth Neel. 2025. Attribute-to-Delete: Machine Unlearning via Datamodel Matching. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_21_1","volume-title":"Revisiting deep learning models for tabular data. Advances in neural information processing systems 34","author":"Gorishniy Yury","year":"2021","unstructured":"Yury Gorishniy, Ivan Rubachev, Valentin Khrulkov, and Artem Babenko. 2021. Revisiting deep learning models for tabular data. Advances in neural information processing systems 34 (2021), 18932\u201318943."},{"key":"e_1_3_2_1_22_1","volume-title":"Why do tree-based models still outperform deep learning on typical tabular data? Advances in neural information processing systems 35","author":"Grinsztajn L\u00e9o","year":"2022","unstructured":"L\u00e9o Grinsztajn, Edouard Oyallon, and Ga\u00ebl Varoquaux. 2022. Why do tree-based models still outperform deep learning on typical tabular data? Advances in neural information processing systems 35 (2022), 507\u2013520."},{"key":"e_1_3_2_1_23_1","volume-title":"Auditing Approximate Machine Unlearning for Differentially Private Models. arXiv preprint arXiv:2508.18671","author":"Gu Yuechun","year":"2025","unstructured":"Yuechun Gu, Jiajie He, and Keke Chen. 2025. Auditing Approximate Machine Unlearning for Differentially Private Models. arXiv preprint arXiv:2508.18671 (2025)."},{"key":"e_1_3_2_1_24_1","volume-title":"Comparison of values of Pearson's and Spearman's correlation coefficients on the same sets of data. Quaestiones geographicae 30, 2","author":"Hauke Jan","year":"2011","unstructured":"Jan Hauke and Tomasz Kossowski. 2011. Comparison of values of Pearson's and Spearman's correlation coefficients on the same sets of data. Quaestiones geographicae 30, 2 (2011), 87\u201393."},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings on Privacy Enhancing Technologies (PoPETs).","author":"Hayes Jamie","year":"2019","unstructured":"Jamie Hayes, Luca Melis, George Danezis, and Emiliano De Cristofaro. 2019. LOGAN: Membership Inference Attacks Against Generative Models. In Proceedings on Privacy Enhancing Technologies (PoPETs)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.053"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the 31st ACM international conference on information & knowledge management. 4064\u20134068","author":"Hyeong Jihyeon","year":"2022","unstructured":"Jihyeon Hyeong, Jayoung Kim, Noseong Park, and Sushil Jajodia. 2022. An empirical study on the membership inference attack against tabular data synthesis models. In Proceedings of the 31st ACM international conference on information & knowledge management. 4064\u20134068."},{"key":"e_1_3_2_1_28_1","unstructured":"itsmesunil. 2022. Bank Loan Modelling. https:\/\/www.kaggle.com\/datasets\/itsmesunil\/bank-loan-modelling. Accessed 2026-02-21. Dataset page states 5 000 observations."},{"key":"e_1_3_2_1_29_1","unstructured":"Matthew Jagielski Om Thakkar Florian Tramer Daphne Ippolito Katherine Lee Nicholas Carlini Eric Wallace Shuang Song Abhradeep Thakurta Nicolas Papernot et al. 2022. Measuring forgetting of memorized training examples. arXiv preprint arXiv:2207.00099 (2022)."},{"key":"e_1_3_2_1_30_1","unstructured":"Hoki Kim Keonwoo Kim Sungwon Chae and Sangwon Yoon. 2025. Unlearning-Aware Minimization. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_31_1","volume-title":"International conference on machine learning. PMLR, 17564\u201317579","author":"Kotelnikov Akim","year":"2023","unstructured":"Akim Kotelnikov, Dmitry Baranchuk, Ivan Rubachev, and Artem Babenko. 2023. Tabddpm: Modelling tabular data with diffusion models. In International conference on machine learning. PMLR, 17564\u201317579."},{"key":"e_1_3_2_1_32_1","volume-title":"Towards unbounded machine unlearning. Advances in neural information processing systems 36","author":"Kurmanji Meghdad","year":"2023","unstructured":"Meghdad Kurmanji, Peter Triantafillou, Jamie Hayes, and Eleni Triantafillou. 2023. Towards unbounded machine unlearning. Advances in neural information processing systems 36 (2023), 1957\u20131987."},{"key":"e_1_3_2_1_33_1","unstructured":"Tobias Leemann Martin Pawelczyk and Gjergji Kasneci. 2023. Gaussian Membership Inference Privacy. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_34_1","first-page":"62821","article-title":"Certified minimax unlearning with generalization rates and deletion capacity","volume":"36","author":"Liu Jiaqi","year":"2023","unstructured":"Jiaqi Liu, Jian Lou, Zhan Qin, and Kui Ren. 2023. Certified minimax unlearning with generalization rates and deletion capacity. Advances in Neural Information Processing Systems 36 (2023), 62821\u201362852.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_35_1","volume-title":"International conference on Machine learning. pmlr, 23803\u201323828","author":"Mao Anqi","year":"2023","unstructured":"Anqi Mao, Mehryar Mohri, and Yutao Zhong. 2023. Cross-entropy loss functions: Theoretical analysis and applications. In International conference on Machine learning. pmlr, 23803\u201323828."},{"key":"e_1_3_2_1_36_1","first-page":"131482","article-title":"Nearly tight black-box auditing of differentially private machine learning","volume":"37","author":"Muthu Selva Annamalai Meenatchi Sundaram","year":"2024","unstructured":"Meenatchi Sundaram Muthu Selva Annamalai and Emiliano De Cristofaro. 2024. Nearly tight black-box auditing of differentially private machine learning. Advances in Neural Information Processing Systems 37 (2024), 131482\u2013131502.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00065"},{"key":"e_1_3_2_1_38_1","unstructured":"Anonymous or as listed in proceedings. 2025. Efficient Verified Unlearning For Distillation. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_39_1","volume-title":"Deep learning on a data diet: Finding important examples early in training. Advances in neural information processing systems 34","author":"Paul Mansheej","year":"2021","unstructured":"Mansheej Paul, Surya Ganguli, and Gintare Karolina Dziugaite. 2021. Deep learning on a data diet: Finding important examples early in training. Advances in neural information processing systems 34 (2021), 20596\u201320607."},{"key":"e_1_3_2_1_40_1","volume-title":"Anna Veronika Dorogush, and Andrey Gulin","author":"Prokhorenkova Liudmila","year":"2018","unstructured":"Liudmila Prokhorenkova, Gleb Gusev, Aleksandr Vorobev, Anna Veronika Dorogush, and Andrey Gulin. 2018. CatBoost: unbiased boosting with categorical features. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2019.23119"},{"key":"e_1_3_2_1_42_1","first-page":"51409","article-title":"Diverse community data for benchmarking data privacy algorithms","volume":"36","author":"Sen Aniruddha","year":"2023","unstructured":"Aniruddha Sen, Christine Task, Dhruv Kapur, Gary Howarth, and Karan Bhagat. 2023. Diverse community data for benchmarking data privacy algorithms. Advances in Neural Information Processing Systems 36 (2023), 51409\u201351420.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"e_1_3_2_1_44_1","volume-title":"Towards probabilistic verification of machine unlearning. arXiv preprint arXiv:2003.04247","author":"Sommer David Marco","year":"2020","unstructured":"David Marco Sommer, Liwei Song, Sameer Wagh, and Prateek Mittal. 2020. Towards probabilistic verification of machine unlearning. arXiv preprint arXiv:2003.04247 (2020)."},{"key":"e_1_3_2_1_45_1","volume-title":"Membership Inference Attacks Against Adversarially Robust Deep Learning Models. In Deep Learning and Security Workshop (DLS) at IEEE S&P.","author":"Song Liwei","year":"2019","unstructured":"Liwei Song and Prateek Mittal. 2019. Membership Inference Attacks Against Adversarially Robust Deep Learning Models. In Deep Learning and Security Workshop (DLS) at IEEE S&P."},{"key":"e_1_3_2_1_46_1","first-page":"49268","article-title":"Privacy auditing with one (1)training run","volume":"36","author":"Steinke Thomas","year":"2023","unstructured":"Thomas Steinke, Milad Nasr, and Matthew Jagielski. 2023. Privacy auditing with one (1)training run. Advances in Neural Information Processing Systems 36 (2023), 49268\u201349280.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_47_1","volume-title":"Dataset cartography: Mapping and diagnosing datasets with training dynamics. arXiv preprint arXiv:2009.10795","author":"Swayamdipta Swabha","year":"2020","unstructured":"Swabha Swayamdipta, Roy Schwartz, Nicholas Lourie, Yizhong Wang, Hannaneh Hajishirzi, Noah A Smith, and Yejin Choi. 2020. Dataset cartography: Mapping and diagnosing datasets with training dynamics. arXiv preprint arXiv:2009.10795 (2020)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3548606.3560554"},{"key":"e_1_3_2_1_49_1","volume-title":"Understanding data importance in machine learning attacks: Does valuable data pose greater harm? arXiv preprint arXiv:2409.03741","author":"Wen Rui","year":"2024","unstructured":"Rui Wen, Michael Backes, and Yang Zhang. 2024. Understanding data importance in machine learning attacks: Does valuable data pose greater harm? arXiv preprint arXiv:2409.03741 (2024)."},{"key":"e_1_3_2_1_50_1","volume-title":"Canary in a coalmine: Better membership inference with ensembled adversarial queries. arXiv preprint arXiv:2210.10750","author":"Wen Yuxin","year":"2022","unstructured":"Yuxin Wen, Arpit Bansal, Hamid Kazemi, Eitan Borgnia, Micah Goldblum, Jonas Geiping, and Tom Goldstein. 2022. Canary in a coalmine: Better membership inference with ensembled adversarial queries. arXiv preprint arXiv:2210.10750 (2022)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3548606.3560675"},{"key":"e_1_3_2_1_52_1","volume-title":"Privacy risk in machine learning: Analyzing the connection to overfitting. In 2018 IEEE 31st computer security foundations symposium (CSF)","author":"Yeom Samuel","unstructured":"Samuel Yeom, Irene Giacomelli, Matt Fredrikson, and Somesh Jha. 2018. Privacy risk in machine learning: Analyzing the connection to overfitting. In 2018 IEEE 31st computer security foundations symposium (CSF). IEEE, 268\u2013282."},{"key":"e_1_3_2_1_53_1","volume-title":"Low-Cost High-Power Membership Inference Attacks. In International Conference on Machine Learning (ICML).","author":"Zarifzadeh Sajjad","year":"2024","unstructured":"Sajjad Zarifzadeh, Pei Liu, and Reza Shokri. 2024. Low-Cost High-Power Membership Inference Attacks. In International Conference on Machine Learning (ICML)."},{"key":"e_1_3_2_1_54_1","volume-title":"Towards Certified Unlearning for Deep Neural Networks. In International Conference on Machine Learning (ICML).","author":"Zhang Binchi","year":"2024","unstructured":"Binchi Zhang, Yushun Dong, Tianhao Wang, and Jundong Li. 2024. Towards Certified Unlearning for Deep Neural Networks. In International Conference on Machine Learning (ICML)."},{"key":"e_1_3_2_1_55_1","volume-title":"Understanding deep learning requires rethinking generalization. arXiv preprint arXiv:1611.03530","author":"Zhang Chiyuan","year":"2016","unstructured":"Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, and Oriol Vinyals. 2016. Understanding deep learning requires rethinking generalization. arXiv preprint arXiv:1611.03530 (2016)."},{"key":"e_1_3_2_1_56_1","volume-title":"Asian conference on machine learning. PMLR, 97\u2013112","author":"Zhao Zilong","year":"2021","unstructured":"Zilong Zhao, Aditya Kunar, Robert Birke, and Lydia Y Chen. 2021. Ctab-gan: Effective table data synthesizing. In Asian conference on machine learning. PMLR, 97\u2013112."}],"event":{"name":"EuroSys '26: 21st European Conference on Computer Systems","location":"Edinburgh Scotland Uk","acronym":"EuroMLSys '26","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the Sixth European Workshop on Machine Learning and Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3805621.3807630","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T13:10:00Z","timestamp":1777381800000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805621.3807630"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,27]]},"references-count":56,"alternative-id":["10.1145\/3805621.3807630","10.1145\/3805621"],"URL":"https:\/\/doi.org\/10.1145\/3805621.3807630","relation":{},"subject":[],"published":{"date-parts":[[2026,4,27]]},"assertion":[{"value":"2026-04-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}