{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T16:48:19Z","timestamp":1755794899727,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3737391","type":"proceedings-article","created":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T21:03:27Z","timestamp":1754255007000},"page":"5379-5390","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Differentially Private Synthetic Data Release for Topics API Outputs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1271-307X","authenticated-orcid":false,"given":"Travis","family":"Dick","sequence":"first","affiliation":[{"name":"Google Research, New York, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0456-3217","authenticated-orcid":false,"given":"Alessandro","family":"Epasto","sequence":"additional","affiliation":[{"name":"Google Research, New York, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1934-8747","authenticated-orcid":false,"given":"Adel","family":"Javanmard","sequence":"additional","affiliation":[{"name":"USC, Los Angeles, CA, USA and Google Research, Los Angeles, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7018-3509","authenticated-orcid":false,"given":"Josh","family":"Karlin","sequence":"additional","affiliation":[{"name":"Google Chrome, Boston, MA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5520-4916","authenticated-orcid":false,"given":"Andr\u00e9s Mu\u00f1oz","family":"Medina","sequence":"additional","affiliation":[{"name":"Google Chrome, New York, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6705-5629","authenticated-orcid":false,"given":"Vahab","family":"Mirrokni","sequence":"additional","affiliation":[{"name":"Google Research, New York, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0235-1624","authenticated-orcid":false,"given":"Sergei","family":"Vassilvitskii","sequence":"additional","affiliation":[{"name":"Google Research, New York, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1136-9538","authenticated-orcid":false,"given":"Peilin","family":"Zhong","sequence":"additional","affiliation":[{"name":"Google Research, New York, NY, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603216.3624959"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3670368"},{"key":"e_1_3_2_2_3_1","volume-title":"Plume: differential privacy at scale. arXiv preprint arXiv:2201.11603","author":"Amin Kareem","year":"2022","unstructured":"Kareem Amin, Jennifer Gillenwater, Matthew Joseph, Alex Kulesza, and Sergei Vassilvitskii. Plume: differential privacy at scale. arXiv preprint arXiv:2201.11603, 2022."},{"key":"e_1_3_2_2_4_1","unstructured":"Apple. AdAttributionKit. Available at https:\/\/ developer.apple.com\/documentation\/AdAttributionKit 2024."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35326-0_52"},{"key":"e_1_3_2_2_6_1","first-page":"457","volume-title":"International Conference on Machine Learning","author":"Aydore Sergul","year":"2021","unstructured":"Sergul Aydore, William Brown, Michael Kearns, Krishnaram Kenthapadi, Luca Melis, Aaron Roth, and Ankit A Siva. Differentially private query release through adaptive projection. In International Conference on Machine Learning, pages 457-467. PMLR, 2021."},{"key":"e_1_3_2_2_7_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Balle Borja","year":"2018","unstructured":"Borja Balle and Yu-Xiang Wang. Improving the gaussian mechanism for differential privacy: Analytical calibration and optimal denoising. In International Conference on Machine Learning. PMLR, 2018."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/SPW63631.2024.00005"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589294"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2218605120"},{"key":"e_1_3_2_2_11_1","volume-title":"Vahab Mirrokni, Sergei Vassilvitskii, and Peilin Zhong. Data release of the DP synthetic Topics API outputs.","author":"Dick Travis","year":"2025","unstructured":"Travis Dick, Alessandro Epasto, Adel Javanmard, Josh Karlin, Andres Munoz Medina, Vahab Mirrokni, Sergei Vassilvitskii, and Peilin Zhong. Data release of the DP synthetic Topics API outputs. Available at https:\/\/www.kaggle.com\/datasets\/googleai\/topics-api-private-data-release\/, 2025."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1561\/0400000042"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/11681878_14"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/1881151.1881152"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978313"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467180"},{"key":"e_1_3_2_2_17_1","unstructured":"Alessandro Epasto Andres Munoz Medina Christina Ilvento and Josh Karlin. Measures of Cross-Site Re-Identification Risk: an Analysis of the Topics API Proposal. https:\/\/github.com\/patcg-individual-drafts\/topics\/blob\/main\/topics_analysis.pdf 2022."},{"key":"e_1_3_2_2_18_1","volume-title":"On the differential privacy and interactivity of privacy sandbox reports. arXiv preprint arXiv:2412.16916","author":"Ghazi Badih","year":"2024","unstructured":"Badih Ghazi, Charlie Harrison, Arpana Hosabettu, Pritish Kamath, Alexander Knop, Ravi Kumar, Ethan Leeman, Pasin Manurangsi, and Vikas Sahu. On the differential privacy and interactivity of privacy sandbox reports. arXiv preprint arXiv:2412.16916, 2024."},{"key":"e_1_3_2_2_19_1","first-page":"309","volume-title":"Proceedings of the 2018 World Wide Web Conference on World Wide Web, WWW 2018","author":"G\u00f3mez-Boix Alejandro","year":"2018","unstructured":"Alejandro G\u00f3mez-Boix, Pierre Laperdrix, and Benoit Baudry. Hiding in the crowd: an analysis of the effectiveness of browser fingerprinting at large scale. In Pierre-Antoine Champin, Fabien Gandon, Mounia Lalmas, and Panagiotis G. Ipeirotis, editors, Proceedings of the 2018 World Wide Web Conference on World Wide Web, WWW 2018, Lyon, France, April 23-27, 2018, pages 309-318. ACM, 2018."},{"volume-title":"The Privacy Sandbox.","year":"2025","key":"e_1_3_2_2_20_1","unstructured":"Google. The Privacy Sandbox. Available at https:\/\/privacysandbox.com\/intl\/en_us\/ (Accessed January 25, 2025), 2025."},{"volume-title":"The Topics API.","year":"2025","key":"e_1_3_2_2_21_1","unstructured":"Google. The Topics API. Available at https:\/\/github.com\/patcg-individual-drafts\/topics (Accessed January 25, 2025), 2025."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3675400"},{"key":"e_1_3_2_2_23_1","volume-title":"Unearthing privacy-enhancing ad technologies (peat): The adoption of google's privacy sandbox. Available at SSRN","author":"Johnson Garrett","year":"2024","unstructured":"Garrett Johnson. Unearthing privacy-enhancing ad technologies (peat): The adoption of google's privacy sandbox. Available at SSRN, 2024."},{"key":"e_1_3_2_2_24_1","volume-title":"3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings","author":"Kingma Diederik P","year":"2015","unstructured":"Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, 2015."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386040"},{"key":"e_1_3_2_2_26_1","volume-title":"Differentially private synthetic data via foundation model apis 1: Images. arXiv preprint arXiv:2305.15560","author":"Lin Zinan","year":"2023","unstructured":"Zinan Lin, Sivakanth Gopi, Janardhan Kulkarni, Harsha Nori, and Sergey Yekhanin. Differentially private synthetic data via foundation model apis 1: Images. arXiv preprint arXiv:2305.15560, 2023."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2012.47"},{"volume-title":"New Privacy Preserving Ads API.","year":"2024","key":"e_1_3_2_2_28_1","unstructured":"Microsoft. New Privacy Preserving Ads API. Available at https:\/\/blogs.windows. com\/msedgedev\/ 2024\/ 03\/ 05\/new-privacy-preserving-ads-api\/ , 2024."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3576915.3616586"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.14649"},{"key":"e_1_3_2_2_31_1","volume-title":"Technical Comments on FLoC Privacy.","author":"Rescorla Eric","year":"2021","unstructured":"Eric Rescorla and Martin Thomson. Technical Comments on FLoC Privacy. Available at https:\/\/mozilla.github.io\/ppa-docs\/floc_report.pdf (2021\/06\/10), 2021."},{"key":"e_1_3_2_2_32_1","volume-title":"Is api access to llms useful for generating private synthetic tabular data?","author":"Swanberg Marika","year":"2025","unstructured":"Marika Swanberg, Ryan McKenna, Edo Roth, Albert Cheu, and Peter Kairouz. Is api access to llms useful for generating private synthetic tabular data?, 2025. URL https:\/\/arxiv.org\/abs\/2502.06555."},{"key":"e_1_3_2_2_33_1","volume-title":"Privacy-preserving in-context learning with differentially private few-shot generation. arXiv preprint arXiv:2309.11765","author":"Tang Xinyu","year":"2023","unstructured":"Xinyu Tang, Richard Shin, Huseyin A Inan, Andre Manoel, Fatemehsadat Mireshghallah, Zinan Lin, Sivakanth Gopi, Janardhan Kulkarni, and Robert Sim. Privacy-preserving in-context learning with differentially private few-shot generation. arXiv preprint arXiv:2309.11765, 2023."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680121.3697810"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"location":"Toronto ON Canada","acronym":"KDD '25"},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3737391","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T14:39:42Z","timestamp":1755355182000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3737391"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":34,"alternative-id":["10.1145\/3711896.3737391","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3737391","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}