{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:19:01Z","timestamp":1759331941121,"version":"3.33.0"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,15]]},"DOI":"10.1109\/bigdata62323.2024.10825249","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:23Z","timestamp":1737052283000},"page":"6379-6386","source":"Crossref","is-referenced-by-count":1,"title":["Private Synthetic Data Generation for Mixed Type Datasets"],"prefix":"10.1109","author":[{"given":"Irene","family":"Tenison","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology,Cambridge,MA"}]},{"given":"Ashley","family":"Chen","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,Cambridge,MA"}]},{"given":"Navpreet","family":"Singh","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,Cambridge,MA"}]},{"given":"Omar","family":"Dahleh","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,Cambridge,MA"}]},{"given":"Eliott","family":"Zemour","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,Cambridge,MA"}]},{"given":"Lalana","family":"Kagal","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,Cambridge,MA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3437984.3458826"},{"article-title":"Gartner identifies top trends shaping the future of data science and machine learning","year":"2023","author":"Gartner","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/BigData55660.2022.10020479"},{"key":"ref5","article-title":"Modeling tabular data using conditional gan","volume":"32","author":"Xu","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Generating faithful synthetic data with large language models: A case study in computational social science","year":"2023","author":"Veselovsky","key":"ref6"},{"article-title":"Propile: Probing privacy leakage in large language models","year":"2023","author":"Kim","key":"ref7"},{"year":"2023","key":"ref8","article-title":"Introducing lakera guard \u2013 bringing enterprise-grade security to llms with one line of code"},{"article-title":"Beyond memorization : Violating privacy via inference with large language models","year":"2023","author":"Staab","key":"ref9"},{"article-title":"Llama 2: Open foundation and fine-tuned chat models","year":"2023","author":"Touvron","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/11681878_14"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"article-title":"Measuring forgetting of memorized training examples","year":"2022","author":"Jagielski","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482281"},{"key":"ref15","article-title":"Large-scale differentially private BERT","volume-title":"CoRR","author":"Anil","year":"2021"},{"article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","year":"2020","author":"Raffel","key":"ref16"},{"key":"ref17","article-title":"When does differentially private learning not suffer in high dimensions?","author":"Li","year":"2022","journal-title":"NeurIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.74"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3592042"},{"article-title":"Privacypreserving domain adaptation of semantic parsers","year":"2022","author":"Mireshghallah","key":"ref20"},{"article-title":"Privacy-preserving recommender systems with synthetic query generation using differentially private large language models","year":"2023","author":"Carranza","key":"ref21"},{"article-title":"Selective differential privacy for language modeling","year":"2021","author":"Shi","key":"ref22"},{"article-title":"Differentially private natural language models: Recent advances and future directions","year":"2023","author":"Hu","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371856"},{"article-title":"On a utilitarian approach to privacy preserving text generation","year":"2021","author":"Zekun Xu","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2775051.2677005"},{"article-title":"One-sided differential privacy","year":"2017","author":"Doudalis","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3534642"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.14778\/3231751.3231757"},{"article-title":"Dtgan: Differential private training for tabular gans","year":"2021","author":"Kunar","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-023-01834-5"},{"article-title":"Table-to-text generation by structure-aware seq2seq learning","year":"2017","author":"Liu","key":"ref32"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11947","article-title":"Order-planning neural text generation from structured data","volume-title":"AAAI Conference on Artificial Intelligence","author":"Sha"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016908"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P19-1195","article-title":"Data-to-text generation with entity modeling","author":"Puduppully","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1128"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11944"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.323"},{"article-title":"Synthetic text generation with differential privacy: A simple and practical recipe","year":"2022","author":"Yue","key":"ref39"},{"article-title":"Large language models can be strong differentially private learners","volume-title":"International Conference on Learning Representations","author":"Li","key":"ref40"},{"key":"ref41","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics","author":"Papineni"},{"key":"ref42","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref43","article-title":"The secret sharer: Evaluating and testing unintended memorization in neural networks","author":"Carlini","year":"2019","journal-title":"USENIX Security"}],"event":{"name":"2024 IEEE International Conference on Big Data (BigData)","start":{"date-parts":[[2024,12,15]]},"location":"Washington, DC, USA","end":{"date-parts":[[2024,12,18]]}},"container-title":["2024 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10824975\/10824942\/10825249.pdf?arnumber=10825249","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:13:53Z","timestamp":1737101633000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10825249\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,15]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/bigdata62323.2024.10825249","relation":{},"subject":[],"published":{"date-parts":[[2024,12,15]]}}}