{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T22:31:50Z","timestamp":1766442710487,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":85,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62572150"],"award-info":[{"award-number":["62572150"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["JCYJ20230807094411024"],"award-info":[{"award-number":["JCYJ20230807094411024"]}]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2024A1515012299"],"award-info":[{"award-number":["2024A1515012299"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,19]]},"DOI":"10.1145\/3719027.3765044","type":"proceedings-article","created":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T23:42:02Z","timestamp":1763854922000},"page":"2354-2368","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Harnessing Sparsification in Federated Learning: A Secure, Efficient, and Differentially Private Realization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5342-7414","authenticated-orcid":false,"given":"Shuangqing","family":"Xu","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, China and The Hong Kong Polytechnic University, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7852-6051","authenticated-orcid":false,"given":"Yifeng","family":"Zheng","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3529-0541","authenticated-orcid":false,"given":"Zhongyun","family":"Hua","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, China"}]}],"member":"320","published-online":{"date-parts":[[2025,11,22]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_3_2_1_1_1","DOI":"10.1145\/2976749.2978318"},{"key":"e_1_3_2_1_2_1","volume-title":"Proc. of NeurIPS.","author":"Agarwal Naman","year":"2021","unstructured":"Naman Agarwal, Peter Kairouz, and Ziyu Liu. 2021. The Skellam Mechanism for Differentially Private Federated Learning. In Proc. of NeurIPS."},{"key":"e_1_3_2_1_3_1","volume-title":"Proc. of NeurIPS.","author":"Andrew Galen","year":"2021","unstructured":"Galen Andrew, Om Thakkar, Brendan McMahan, and Swaroop Ramaswamy. 2021. Differentially Private Learning with Adaptive Clipping. In Proc. of NeurIPS."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_4_1","DOI":"10.1145\/2976749.2978331"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_5_1","DOI":"10.1145\/3460120.3484560"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_6_1","DOI":"10.1145\/3548606.3560691"},{"key":"e_1_3_2_1_7_1","volume-title":"Can Karakus, and Suhas N. Diggavi.","author":"Basu Debraj","year":"2019","unstructured":"Debraj Basu, Deepesh Data, Can Karakus, and Suhas N. Diggavi. 2019. Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification and Local Computations. In Proc. of NeurIPS."},{"key":"e_1_3_2_1_8_1","volume-title":"Proc. of USENIX Security.","author":"Bell James","year":"2023","unstructured":"James Bell, Adri\u00e0 Gasc\u00f3n, Tancr\u00e8de Lepoint, Baiyu Li, Sarah Meiklejohn, Mariana Raykova, and Cathie Yun. 2023. ACORN: Input Validation for Secure Aggregation. In Proc. of USENIX Security."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_9_1","DOI":"10.1145\/3372297.3417885"},{"key":"e_1_3_2_1_10_1","volume-title":"Kolmogorov-smirnov test: Overview","author":"Berger Vance W","year":"2014","unstructured":"Vance W Berger and YanYan Zhou. 2014. Kolmogorov-smirnov test: Overview. Wiley statsref: Statistics reference online (2014)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_11_1","DOI":"10.1145\/3133956.3133982"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_12_1","DOI":"10.1109\/SP54263.2024.00164"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_13_1","DOI":"10.1007\/978-3-030-57990-6_11"},{"key":"e_1_3_2_1_14_1","volume-title":"Proc. of NeurIPS.","author":"Canonne Cl\u00e9ment L.","year":"2020","unstructured":"Cl\u00e9ment L. Canonne, Gautam Kamath, and Thomas Steinke. 2020. The Discrete Gaussian for Differential Privacy. In Proc. of NeurIPS."},{"key":"e_1_3_2_1_15_1","volume-title":"Proc. of ESORICS.","author":"Pathum Chamikara Mahawaga Arachchige","year":"2022","unstructured":"Mahawaga Arachchige Pathum Chamikara, Dongxi Liu, Seyit Camtepe, Surya Nepal, Marthie Grobler, Peter Bert\u00f3k, and Ibrahim Khalil. 2022. Local Differential Privacy for Federated Learning. In Proc. of ESORICS."},{"key":"e_1_3_2_1_16_1","volume-title":"Secret-Shared Shuffle. In Proc. of ASIACRYPT.","author":"Chase Melissa","year":"2020","unstructured":"Melissa Chase, Esha Ghosh, and Oxana Poburinnaya. 2020. Secret-Shared Shuffle. In Proc. of ASIACRYPT."},{"key":"e_1_3_2_1_17_1","volume-title":"Proc. of ICML.","author":"Chen Wei-Ning","year":"2022","unstructured":"Wei-Ning Chen, Christopher A. Choquette-Choo, Peter Kairouz, and Ananda Theertha Suresh. 2022. The Fundamental Price of Secure Aggregation in Differentially Private Federated Learning. In Proc. of ICML."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_18_1","DOI":"10.1109\/CVPR52688.2022.00988"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_19_1","DOI":"10.1007\/978-3-319-96878-0_2"},{"key":"e_1_3_2_1_20_1","volume-title":"Proc. of ICLR.","author":"Choquette-Choo Christopher A.","year":"2021","unstructured":"Christopher A. Choquette-Choo, Natalie Dullerud, Adam Dziedzic, Yunxiang Zhang, Somesh Jha, Nicolas Papernot, and Xiao Wang. 2021. CaPC Learning: Confidential and Private Collaborative Learning. In Proc. of ICLR."},{"key":"e_1_3_2_1_21_1","volume-title":"Proc. of USENIX NSDI.","author":"Corrigan-Gibbs Henry","year":"2017","unstructured":"Henry Corrigan-Gibbs and Dan Boneh. 2017. Prio: Private, Robust, and Scalable Computation of Aggregate Statistics. In Proc. of USENIX NSDI."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_22_1","DOI":"10.56553\/popets-2025-0010"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_23_1","DOI":"10.1109\/SP46214.2022.9833611"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_24_1","DOI":"10.1016\/0020-0190(78)90067-4"},{"key":"e_1_3_2_1_25_1","first-page":"3","article-title":"The Algorithmic Foundations of Differential Privacy","volume":"9","author":"Dwork Cynthia","year":"2014","unstructured":"Cynthia Dwork and Aaron Roth. 2014. The Algorithmic Foundations of Differential Privacy. Found. Trends Theor. Comput. Sci., Vol. 9, 3-4 (2014), 211-407.","journal-title":"Found. Trends Theor. Comput. Sci."},{"key":"e_1_3_2_1_26_1","volume-title":"Hasin Us Sami, and Basak Guler","author":"Erg\u00fcn Irem","year":"2021","unstructured":"Irem Erg\u00fcn, Hasin Us Sami, and Basak Guler. 2021. Sparsified Secure Aggregation for Privacy-Preserving Federated Learning. CoRR, Vol. abs\/2112.12872 (2021)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_27_1","DOI":"10.14722\/ndss.2022.24141"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_28_1","DOI":"10.1145\/3658644.3690257"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_29_1","DOI":"10.1109\/SPW59333.2023.00012"},{"key":"e_1_3_2_1_30_1","volume-title":"In Proc. of AISTATS.","author":"Geng Quan","year":"2020","unstructured":"Quan Geng, Wei Ding, Ruiqi Guo, and Sanjiv Kumar. 2020. In Proc. of AISTATS."},{"key":"e_1_3_2_1_31_1","volume-title":"Proc. of NeurIPS Workshop: Machine Learning on the Phone and other Consumer Devices.","author":"Geyer Robin C.","year":"2017","unstructured":"Robin C. Geyer, Tassilo Klein, and Moin Nabi. 2017. Differentially Private Federated Learning: A Client Level Perspective. In Proc. of NeurIPS Workshop: Machine Learning on the Phone and other Consumer Devices."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_32_1","DOI":"10.1137\/120880811"},{"unstructured":"Google Privacy Team. 2020. Secure Noise Generation. Google.","key":"e_1_3_2_1_33_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_34_1","DOI":"10.1145\/3658644.3690281"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_35_1","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_36_1","DOI":"10.1109\/TMC.2023.3343288"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_37_1","DOI":"10.1145\/3517820"},{"key":"e_1_3_2_1_38_1","volume-title":"Proc. of ICML.","author":"Kairouz Peter","year":"2021","unstructured":"Peter Kairouz, Ziyu Liu, and Thomas Steinke. 2021a. The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation. In Proc. of ICML."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_39_1","DOI":"10.1561\/2200000083"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_40_1","DOI":"10.14778\/3603581.3603583"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_41_1","DOI":"10.1145\/3664476.3664490"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_42_1","DOI":"10.1145\/3372297.3417872"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_43_1","DOI":"10.1109\/EuroSP51992.2021.00029"},{"key":"e_1_3_2_1_44_1","volume-title":"Proc. of UAI.","author":"Kerkouche Raouf","year":"2021","unstructured":"Raouf Kerkouche, Gergely \u00c1cs, Claude Castelluccia, and Pierre Genev\u00e8s. 2021b. Constrained differentially private federated learning for low-bandwidth devices. In Proc. of UAI."},{"unstructured":"Alex Krizhevsky Geoffrey Hinton et al. 2009. Learning multiple layers of features from tiny images. (2009).","key":"e_1_3_2_1_45_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_46_1","DOI":"10.1109\/5.726791"},{"doi-asserted-by":"crossref","unstructured":"Yehuda Lindell. 2017. How to Simulate It - A Tutorial on the Simulation Proof Technique. (2017) 277-346.","key":"e_1_3_2_1_47_1","DOI":"10.1007\/978-3-319-57048-8_6"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_48_1","DOI":"10.1145\/3658644.3670351"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_49_1","DOI":"10.1007\/978-3-030-59410-7_33"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_50_1","DOI":"10.1016\/j.cose.2022.102993"},{"key":"e_1_3_2_1_51_1","volume-title":"Proc. of AISTATS.","author":"McMahan Brendan","year":"2017","unstructured":"Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Ag\u00fcera y Arcas. 2017. Communication-Efficient Learning of Deep Networks from Decentralized Data. In Proc. of AISTATS."},{"key":"e_1_3_2_1_52_1","volume-title":"Proc. of ICLR.","author":"McMahan H. Brendan","year":"2018","unstructured":"H. Brendan McMahan, Daniel Ramage, Kunal Talwar, and Li Zhang. 2018. Learning Differentially Private Recurrent Language Models. In Proc. of ICLR."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_53_1","DOI":"10.1109\/SP.2019.00029"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_54_1","DOI":"10.1145\/3564625.3567973"},{"key":"e_1_3_2_1_55_1","volume-title":"Proc. of IEEE CSF.","author":"Mironov Ilya","year":"2017","unstructured":"Ilya Mironov. 2017. R\u00e9nyi Differential Privacy. In Proc. of IEEE CSF."},{"key":"e_1_3_2_1_56_1","first-page":"1","article-title":"PLASMA: Private, Lightweight Aggregated Statistics against Malicious Adversaries","volume":"2024","author":"Mouris Dimitris","year":"2024","unstructured":"Dimitris Mouris, Pratik Sarkar, and Nektarios Georgios Tsoutsos. 2024. PLASMA: Private, Lightweight Aggregated Statistics against Malicious Adversaries. Proc. Priv. Enhancing Technol., Vol. 2024, 3 (2024), 1-19.","journal-title":"Proc. Priv. Enhancing Technol."},{"key":"e_1_3_2_1_57_1","volume-title":"Pegah Nikbakht Bideh, and Joakim Brorsson","author":"Nilsson Alexander","year":"2020","unstructured":"Alexander Nilsson, Pegah Nikbakht Bideh, and Joakim Brorsson. 2020. A Survey of Published Attacks on Intel SGX. CoRR, Vol. abs\/2006.13598 (2020)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_58_1","DOI":"10.1109\/SP46215.2023.10179468"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_59_1","DOI":"10.1109\/SP54263.2024.00245"},{"key":"e_1_3_2_1_60_1","volume-title":"Proc. of ICLR.","author":"Reddi Sashank J.","year":"2021","unstructured":"Sashank J. Reddi, Zachary Charles, Manzil Zaheer, Zachary Garrett, Keith Rush, Jakub Kone\u010dn\u00fd, Sanjiv Kumar, and Hugh Brendan McMahan. 2021. Adaptive Federated Optimization. In Proc. of ICLR."},{"key":"e_1_3_2_1_61_1","volume-title":"Proc. of SIGMOD.","author":"Chowdhury Amrita Roy","year":"2020","unstructured":"Amrita Roy Chowdhury, Chenghong Wang, Xi He, Ashwin Machanavajjhala, and Somesh Jha. 2020. Crypt\u03b5: Crypto-assisted differential privacy on untrusted servers. In Proc. of SIGMOD."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_62_1","DOI":"10.1109\/SP46215.2023.10179422"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_63_1","DOI":"10.1145\/322217.322225"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_64_1","DOI":"10.1109\/CVPR52729.2023.02352"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_65_1","DOI":"10.1109\/SP.2017.41"},{"key":"e_1_3_2_1_66_1","volume-title":"Near","author":"Stevens Timothy","year":"2022","unstructured":"Timothy Stevens, Christian Skalka, Christelle Vincent, John H. Ring, Samuel Clark, and Joseph P. Near. 2022. Efficient Differentially Private Secure Aggregation for Federated Learning via Hardness of Learning with Errors. In Proc. of USENIX Security."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_67_1","DOI":"10.24963\/ijcai.2021\/217"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_68_1","DOI":"10.1109\/TIFS.2024.3375527"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_69_1","DOI":"10.1145\/3378679.3394533"},{"key":"e_1_3_2_1_70_1","volume-title":"Proc. of USENIX Security.","author":"Vadapalli Adithya","year":"2023","unstructured":"Adithya Vadapalli, Ryan Henry, and Ian Goldberg. 2023. DUORAM: A Bandwidth-Efficient Distributed ORAM for 2- and 3-Party Computation. In Proc. of USENIX Security."},{"key":"e_1_3_2_1_71_1","volume-title":"Proc. of UAI.","author":"Wang Lingxiao","year":"2023","unstructured":"Lingxiao Wang, Bargav Jayaraman, David Evans, and Quanquan Gu. 2023. Efficient Privacy-Preserving Stochastic Nonconvex Optimization. In Proc. of UAI."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_72_1","DOI":"10.1109\/ICDE.2019.00063"},{"key":"e_1_3_2_1_73_1","volume-title":"Proc. of AISTATS.","author":"Wang Yu-Xiang","year":"2019","unstructured":"Yu-Xiang Wang, Borja Balle, and Shiva Prasad Kasiviswanathan. 2019a. Subsampled Renyi Differential Privacy and Analytical Moments Accountant. In Proc. of AISTATS."},{"key":"e_1_3_2_1_74_1","volume-title":"Proc. of AISTATS.","author":"Wang Yu-Xiang","year":"2019","unstructured":"Yu-Xiang Wang, Borja Balle, and Shiva Prasad Kasiviswanathan. 2019b. Subsampled r\u00e9nyi differential privacy and analytical moments accountant. In Proc. of AISTATS."},{"key":"e_1_3_2_1_75_1","volume-title":"Proc. of NeurIPS.","author":"Wangni Jianqiao","year":"2018","unstructured":"Jianqiao Wangni, Jialei Wang, Ji Liu, and Tong Zhang. 2018. Gradient Sparsification for Communication-Efficient Distributed Optimization. In Proc. of NeurIPS."},{"key":"e_1_3_2_1_76_1","volume-title":"Proc. of USENIX Security.","author":"Watson Jean-Luc","year":"2022","unstructured":"Jean-Luc Watson, Sameer Wagh, and Raluca Ada Popa. 2022. Piranha: A GPU Platform for Secure Computation. In Proc. of USENIX Security."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_77_1","DOI":"10.1016\/0022-0000(81)90033-7"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_78_1","DOI":"10.1145\/3576915.3616641"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_79_1","DOI":"10.1145\/3589264"},{"key":"e_1_3_2_1_80_1","volume-title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms. CoRR","author":"Xiao Han","year":"2017","unstructured":"Han Xiao, Kashif Rasul, and Roland Vollgraf. 2017. Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms. CoRR, Vol. abs\/1708.07747 (2017)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_81_1","DOI":"10.1145\/3658644.3690200"},{"key":"e_1_3_2_1_82_1","volume-title":"Harnessing Sparsification in Federated Learning: A Secure, Efficient, and Differentially Private Realization. CoRR","author":"Xu Shuangqing","year":"2025","unstructured":"Shuangqing Xu, Yifeng Zheng, and Zhongyun Hua. 2025. Harnessing Sparsification in Federated Learning: A Secure, Efficient, and Differentially Private Realization. CoRR (2025)."},{"key":"e_1_3_2_1_83_1","volume-title":"Proc. of USENIX Security.","author":"Yang Yuchen","year":"2023","unstructured":"Yuchen Yang, Bo Hui, Haolin Yuan, Neil Zhenqiang Gong, and Yinzhi Cao. 2023. PrivateFL: Accurate, Differentially Private Federated Learning via Personalized Data Transformation. In Proc. of USENIX Security."},{"key":"e_1_3_2_1_84_1","volume-title":"Proc. of NeurIPS.","author":"Zhu Ligeng","year":"2019","unstructured":"Ligeng Zhu, Zhijian Liu, and Song Han. 2019. Deep Leakage from Gradients. In Proc. of NeurIPS."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_85_1","DOI":"10.1007\/3-540-09519-5_73"}],"event":{"sponsor":["SIGSAC ACM Special Interest Group on Security, Audit, and Control"],"acronym":"CCS '25","name":"CCS '25: ACM SIGSAC Conference on Computer and Communications Security","location":"Taipei Taiwan"},"container-title":["Proceedings of the 2025 ACM SIGSAC Conference on Computer and Communications Security"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3719027.3765044","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T22:27:09Z","timestamp":1766442429000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3719027.3765044"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,19]]},"references-count":85,"alternative-id":["10.1145\/3719027.3765044","10.1145\/3719027"],"URL":"https:\/\/doi.org\/10.1145\/3719027.3765044","relation":{},"subject":[],"published":{"date-parts":[[2025,11,19]]},"assertion":[{"value":"2025-11-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}