{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T02:34:06Z","timestamp":1755225246734,"version":"3.43.0"},"publisher-location":"New York, NY, USA","reference-count":68,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,25]]},"DOI":"10.1145\/3708821.3736203","type":"proceedings-article","created":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T06:30:56Z","timestamp":1755066656000},"page":"163-179","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Prior-Based Label Differential Privacy via Secure Two-Party Computation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7642-1341","authenticated-orcid":false,"given":"Amit","family":"Agarwal","sequence":"first","affiliation":[{"name":"University of Illinois Urbana-Champaign, Champaign, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6247-4255","authenticated-orcid":false,"given":"Stanislav","family":"Peceny","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1744-4025","authenticated-orcid":false,"given":"Mariana","family":"Raykova","sequence":"additional","affiliation":[{"name":"Google, New York, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7951-3930","authenticated-orcid":false,"given":"Phillipp","family":"Schoppmann","sequence":"additional","affiliation":[{"name":"Google, New York, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5735-3524","authenticated-orcid":false,"given":"Karn","family":"Seth","sequence":"additional","affiliation":[{"name":"Google, New York, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,8,24]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"2023. Privacy-preserving metrics for Firefox. https:\/\/divviup.org\/blog\/divvi-up-in-firefox\/."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3524944"},{"key":"e_1_3_3_2_5_2","volume-title":"Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security, CCS 2019, London, UK, November 11-15, 2019","author":"Agrawal Nitin","unstructured":"Nitin Agrawal, Ali\u00a0Shahin Shamsabadi, Matt\u00a0J. Kusner, and Adri\u00e0 Gasc\u00f3n. [n. d.]. QUOTIENT: Two-Party Secure Neural Network Training and Prediction. In Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security, CCS 2019, London, UK, November 11-15, 2019, Lorenzo Cavallaro, Johannes Kinder, XiaoFeng Wang, and Jonathan Katz (Eds.)."},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/2508859.2516738"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44750-48"},{"key":"e_1_3_3_2_8_2","first-page":"1253","volume-title":"CCS","author":"Bell James\u00a0Henry","year":"2020","unstructured":"James\u00a0Henry Bell, Kallista\u00a0A. Bonawitz, Adri\u00e0 Gasc\u00f3n, Tancr\u00e8de Lepoint, and Mariana Raykova. 2020. Secure Single-Server Aggregation with (Poly)Logarithmic Overhead. In CCS. ACM, 1253\u20131269."},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/62212.62213"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3576915.3616681"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132769"},{"key":"e_1_3_3_2_12_2","volume-title":"MLSys","author":"Bonawitz Kallista\u00a0A.","year":"2019","unstructured":"Kallista\u00a0A. Bonawitz, Hubert Eichner, Wolfgang Grieskamp, Dzmitry Huba, Alex Ingerman, Vladimir Ivanov, Chlo\u00e9 Kiddon, Jakub Kone\u010dn\u00fd, Stefano Mazzocchi, Brendan McMahan, Timon\u00a0Van Overveldt, David Petrou, Daniel Ramage, and Jason Roselander. 2019. Towards Federated Learning at Scale: System Design. In MLSys. mlsys.org."},{"key":"e_1_3_3_2_13_2","first-page":"1175","volume-title":"CCS","author":"Bonawitz Kallista\u00a0A.","year":"2017","unstructured":"Kallista\u00a0A. Bonawitz, Vladimir Ivanov, Ben Kreuter, Antonio Marcedone, H.\u00a0Brendan McMahan, Sarvar Patel, Daniel Ramage, Aaron Segal, and Karn Seth. 2017. Practical Secure Aggregation for Privacy-Preserving Machine Learning. In CCS. ACM, 1175\u20131191."},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-36030-6_14"},{"key":"e_1_3_3_2_15_2","unstructured":"Google Brain. 2015. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. https:\/\/www.tensorflow.org\/."},{"key":"e_1_3_3_2_16_2","first-page":"234","volume-title":"Conference on the Theory and Application of Cryptographic Techniques","author":"Brassard Gilles","year":"1986","unstructured":"Gilles Brassard, Claude Cr\u00e9peau, and Jean-Marc Robert. 1986. All-or-nothing disclosure of secrets. In Conference on the Theory and Application of Cryptographic Techniques. Springer, 234\u2013238."},{"key":"e_1_3_3_2_17_2","first-page":"3233","volume-title":"International Conference on Machine Learning","author":"Busa-Fekete Robert\u00a0Istvan","year":"2023","unstructured":"Robert\u00a0Istvan Busa-Fekete, Andres\u00a0Munoz Medina, Umar Syed, and Sergei Vassilvitskii. 2023. Label differential privacy and private training data release. In International Conference on Machine Learning. PMLR, 3233\u20133251."},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.2001.959888"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3354256"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-17653-213"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-22365-5_13"},{"key":"e_1_3_3_2_22_2","unstructured":"Fran\u00e7ois Chollet et\u00a0al. 2015. Keras. https:\/\/keras.io."},{"key":"e_1_3_3_2_23_2","first-page":"769","volume-title":"Annual International Cryptology Conference. Springer","author":"Cramer Ronald","year":"2018","unstructured":"Ronald Cramer, Ivan Damg\u00e5rd, Daniel Escudero, Peter Scholl, and Chaoping Xing. 2018. SPDZ2k: Efficient MPC mod 2k for Dishonest Majority. In Annual International Cryptology Conference. Springer. 769\u2013798."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32009-5_38"},{"key":"e_1_3_3_2_25_2","unstructured":"Sankha Das Sayak\u00a0Ray Chowdhury Nishanth Chandran Divya Gupta Satya Lokam and Rahul Sharma. 2024. Communication Efficient Secure and Private Multi-Party Deep Learning. Cryptology ePrint Archive (2024)."},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Li Deng. 2012. The mnist database of handwritten digit images for machine learning research. IEEE Signal Processing Magazine 29 6 (2012) 141\u2013142.","DOI":"10.1109\/MSP.2012.2211477"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45539-6_10"},{"key":"e_1_3_3_2_28_2","volume-title":"Proceedings of the AdKDD and TargetAd Workshop, KDD, London,United Kingdom, August, 20, 2018","author":"Artem Diemert Eustache, Betlei","year":"2018","unstructured":"Diemert Eustache, Betlei Artem, Christophe Renaudin, and Amini Massih-Reza. 2018. A Large Scale Benchmark for Uplift Modeling. In Proceedings of the AdKDD and TargetAd Workshop, KDD, London,United Kingdom, August, 20, 2018. ACM."},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1007\/11761679_29"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1007\/1168187814"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1007\/11681878_14"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"crossref","unstructured":"Reo Eriguchi Atsunori Ichikawa Noboru Kunihiro and Koji Nuida. 2022. Efficient noise generation protocols for differentially private multiparty computation. IEEE Transactions on Dependable and Secure Computing 20 6 (2022) 4486\u20134501.","DOI":"10.1109\/TDSC.2022.3227568"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611975482.151"},{"key":"e_1_3_3_2_34_2","first-page":"7055","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Esfandiari Hossein","year":"2022","unstructured":"Hossein Esfandiari, Vahab Mirrokni, Umar Syed, and Sergei Vassilvitskii. 2022. Label differential privacy via clustering. In International Conference on Artificial Intelligence and Statistics. PMLR, 7055\u20137075."},{"key":"e_1_3_3_2_35_2","volume-title":"Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual","author":"Esmaeili Mani\u00a0Malek","year":"2021","unstructured":"Mani\u00a0Malek Esmaeili, Ilya Mironov, Karthik Prasad, Igor Shilov, and Florian Tram\u00e8r. 2021. Antipodes of Label Differential Privacy: PATE and ALIBI. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, Marc\u2019Aurelio Ranzato, Alina Beygelzimer, Yann\u00a0N. Dauphin, Percy Liang, and Jennifer\u00a0Wortman Vaughan (Eds.)."},{"key":"e_1_3_3_2_36_2","unstructured":"Badih Ghazi Noah Golowich Ravi Kumar Pasin Manurangsi and Chiyuan Zhang. 2021. Deep learning with label differential privacy. Advances in neural information processing systems 34 (2021) 27131\u201327145."},{"key":"e_1_3_3_2_37_2","unstructured":"Badih Ghazi Pritish Kamath Ravi Kumar Ethan Leeman Pasin Manurangsi Avinash Varadarajan and Chiyuan Zhang. 2022. Regression with Label Differential Privacy. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2212.06074 (2022)."},{"key":"e_1_3_3_2_38_2","volume-title":"Foundations of Cryptography: Volume 2, Basic Applications","author":"Goldreich Oded","year":"2009","unstructured":"Oded Goldreich. 2009. Foundations of Cryptography: Volume 2, Basic Applications. Cambridge University Press."},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"crossref","unstructured":"Xueluan Gong Qian Wang Yanjiao Chen Wang Yang and Xinchang Jiang. 2021. Model extraction attacks and defenses on cloud-based machine learning models. IEEE Communications Magazine 58 12 (2021) 83\u201389.","DOI":"10.1109\/MCOM.001.2000196"},{"key":"e_1_3_3_2_40_2","unstructured":"Google. 2022. Bazel. https:\/\/bazel.build\/."},{"key":"e_1_3_3_2_41_2","unstructured":"Google. 2023. GoogleTest \u2013 Google Testing and Mocking Framework. https:\/\/github.com\/google\/googletest."},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP40000.2020.00016"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.56553\/popets-2023-0118"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-45146-4_9"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-36594-2_34"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3664476.3664490"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3372297.3417872"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/62212.62215"},{"key":"e_1_3_3_2_49_2","unstructured":"Alex Krizhevsky. 2009. CIFAR-10 (Canadian Institute for Advanced Research). (2009). http:\/\/www.cs.toronto.edu\/\u00a0kriz\/cifar.html"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/1132516.1132532"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.1997.646125"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3634737.3657002"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"crossref","unstructured":"Yehuda Lindell. 2017. How to simulate it\u2013a tutorial on the simulation proof technique. Tutorials on the Foundations of Cryptography: Dedicated to Oded Goldreich (2017) 277\u2013346.","DOI":"10.1007\/978-3-319-57048-8_6"},{"key":"e_1_3_3_2_54_2","unstructured":"Mani Malek\u00a0Esmaeili Ilya Mironov Karthik Prasad Igor Shilov and Florian Tramer. 2021. Antipodes of label differential privacy: Pate and alibi. Advances in Neural Information Processing Systems 34 (2021) 6934\u20136945."},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/2382196.2382264"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/301250.301312"},{"key":"e_1_3_3_2_57_2","unstructured":"PATCG. 2023. Private Conversion Optimisation. https:\/\/github.com\/patcg\/meetings\/issues\/117."},{"key":"e_1_3_3_2_58_2","volume-title":"Usenix Security Symposium 2023","author":"Rathee Deevashwer","year":"2023","unstructured":"Deevashwer Rathee, Anwesh Bhattacharya, Divya Gupta, Rahul Sharma, and Dawn Song. 2023. Secure Floating-Point Training. In Usenix Security Symposium 2023."},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3372297.3417274"},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"crossref","unstructured":"C\u00e9sar Sabater Florian Hahn Andreas Peter and Jan Ramon. 2023. Private sampling with identifiable cheaters. Proceedings on Privacy Enhancing Technologies 2023 2 (2023).","DOI":"10.56553\/popets-2023-0058"},{"key":"e_1_3_3_2_61_2","unstructured":"XU Shirong Chendi Wang Will\u00a0Wei Sun and Guang Cheng. 2023. Binary classification under local label differential privacy using randomized response mechanisms. Transactions on Machine Learning Research (2023)."},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"crossref","unstructured":"Tatsuya Takemura Naoto Yanai and Toru Fujiwara. 2020. Model extraction attacks on recurrent neural networks. Journal of Information Processing 28 (2020) 1010\u20131024.","DOI":"10.2197\/ipsjjip.28.1010"},{"key":"e_1_3_3_2_63_2","doi-asserted-by":"crossref","unstructured":"Kunal Talwar Shan Wang Audra McMillan Vojta Jina Vitaly Feldman Bailey Basile Aine Cahill Yi\u00a0Sheng Chan Mike Chatzidakis Junye Chen Oliver Chick Mona Chitnis Suman Ganta Yusuf Goren Filip Granqvist Kristine Guo Frederic Jacobs Omid Javidbakht Albert Liu Richard Low Dan Mascenik Steve Myers David Park Wonhee Park Gianni Parsa Tommy Pauly Christian Priebe Rehan Rishi Guy Rothblum Michael Scaria Linmao Song Congzheng Song Karl Tarbe Sebastian Vogt Luke Winstrom and Shundong Zhou. 2023. Samplable Anonymous Aggregation for Private Federated Data Analysis. arxiv:https:\/\/arXiv.org\/abs\/2307.15017\u00a0[cs.CR]","DOI":"10.1145\/3658644.3690224"},{"key":"e_1_3_3_2_64_2","unstructured":"Erik Taubeneck Ben Savage and Martin Thomson. 2022. Interoperable Private Attribution (IPA). https:\/\/docs.google.com\/document\/d\/1KpdSKD8-Rn0bWPTu4UtK54ks0yv2j22pA5SrAD9av4s."},{"key":"e_1_3_3_2_65_2","doi-asserted-by":"crossref","unstructured":"Sameer Wagh Divya Gupta and Nishanth Chandran. 2019. SecureNN: 3-Party Secure Computation for Neural Network Training. Proc. Priv. Enhancing Technol. 2019 3 (2019) 26\u201349.","DOI":"10.2478\/popets-2019-0035"},{"key":"e_1_3_3_2_66_2","doi-asserted-by":"crossref","unstructured":"Stanley\u00a0L Warner. 1965. Randomized response: A survey technique for eliminating evasive answer bias. J. Amer. Statist. Assoc. 60 309 (1965) 63\u201369.","DOI":"10.1080\/01621459.1965.10480775"},{"key":"e_1_3_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/TrustCom.2016.0157"},{"key":"e_1_3_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.1986.25"},{"key":"e_1_3_3_2_69_2","volume-title":"NeurIPS 2021 Workshop Privacy in Machine Learning","author":"Yuan Sen","year":"2021","unstructured":"Sen Yuan, Milan Shen, Ilya Mironov, and Anderson Nascimento. 2021. Label private deep learning training based on secure multiparty computation and differential privacy. In NeurIPS 2021 Workshop Privacy in Machine Learning."}],"event":{"name":"ASIA CCS '25: 20th ACM Asia Conference on Computer and Communications Security","location":"Hanoi Vietnam","acronym":"ASIA CCS '25","sponsor":["SIGSAC ACM Special Interest Group on Security, Audit, and Control"]},"container-title":["Proceedings of the 20th ACM Asia Conference on Computer and Communications Security"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3708821.3736203","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T07:30:20Z","timestamp":1755070220000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3708821.3736203"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,24]]},"references-count":68,"alternative-id":["10.1145\/3708821.3736203","10.1145\/3708821"],"URL":"https:\/\/doi.org\/10.1145\/3708821.3736203","relation":{},"subject":[],"published":{"date-parts":[[2025,8,24]]},"assertion":[{"value":"2025-08-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}