{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T07:01:12Z","timestamp":1764831672336,"version":"3.46.0"},"reference-count":247,"publisher":"Tech Science Press","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["CMC"],"published-print":{"date-parts":[[2025]]},"DOI":"10.32604\/cmc.2025.068875","type":"journal-article","created":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T07:59:53Z","timestamp":1757318393000},"page":"2527-2578","source":"Crossref","is-referenced-by-count":0,"title":["On Privacy-Preserved Machine Learning Using Secure Multi-Party Computing: Techniques and Trends"],"prefix":"10.32604","volume":"85","author":[{"given":"Oshan","family":"Mudannayake","sequence":"first","affiliation":[]},{"given":"Amila","family":"Indika","sequence":"additional","affiliation":[]},{"given":"Upul","family":"Jayasinghe","sequence":"additional","affiliation":[]},{"given":"Gyu Myoung","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Janaka","family":"Alawatugoda","sequence":"additional","affiliation":[]}],"member":"17807","published-online":{"date-parts":[[2025]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Zhang C, Li S. State-of-the-art approaches to enhancing privacy preservation of machine learning datasets: a survey. arXiv:2404.16847. 2025.","key":"ref1","DOI":"10.36227\/techrxiv.170956580.07799070\/v1"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1186\/s42400-024-00343-4","article-title":"Efficient and secure multi-party computation protocol supporting deep learning","volume":"8","author":"Zhang","year":"2025","journal-title":"Cybersecurity"},{"key":"ref3","series-title":"Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; 2007 Aug 12\u201315","first-page":"775","article-title":"Privacy-preservation for gradient descent methods","author":"Wan"},{"key":"ref4","series-title":"International Conference on Financial Cryptography and Data Security","first-page":"128","article-title":"Privacy-preserving classifier learning","author":"Brickell","year":"2009"},{"year":"2010","author":"Pathak","journal-title":"Advances in neural information processing systems","key":"ref5"},{"key":"ref6","series-title":"Annual Cryptology Conference","first-page":"643","article-title":"Multiparty computation from somewhat homomorphic encryption","author":"Damg\u00e5rd","year":"2012"},{"key":"ref7","series-title":"2017 IEEE Symposium on Security and Privacy (SP); 2017 May 22\u201326","first-page":"19","article-title":"Secureml: a system for scalable privacy-preserving machine learning","author":"Mohassel"},{"key":"ref8","series-title":"Proceedings of the 2018 on Asia Conference on Computer and Communications Security; 2018 Jun 4\u20138","first-page":"707","article-title":"Chameleon: a hybrid secure computation framework for machine learning applications","author":"Riazi"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"26","DOI":"10.2478\/popets-2019-0035","article-title":"SecureNN: 3-party secure computation for neural network training","volume":"2019","author":"Wagh","year":"2019","journal-title":"Proc Priv Enhancing Technol"},{"key":"ref10","series-title":"Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security; 2019 Nov 11\u201315","first-page":"1231","article-title":"QUOTIENT: two-party secure neural network training and prediction","author":"Agrawal"},{"key":"ref11","series-title":"2020 IEEE Symposium on Security and Privacy (SP); 2020 May 18\u201321","first-page":"336","article-title":"Cryptflow: secure tensorflow inference","author":"Kumar"},{"key":"ref12","first-page":"4961","article-title":"Crypten: secure multi-party computation meets machine learning","volume":"34","author":"Knott","year":"2021","journal-title":"Adv Neu Inform Process Syst"},{"doi-asserted-by":"crossref","unstructured":"Wagh S, Tople S, Benhamouda F, Kushilevitz E, Mittal P, Rabin T. Falcon: honest-majority maliciously secure framework for private deep learning. arXiv:2004.02229. 2020. doi:10.48550\/arxiv.2004.02229.","key":"ref13","DOI":"10.2478\/popets-2021-0011"},{"key":"ref14","series-title":"31st USENIX Security Symposium (USENIX Security 22); 2022 Aug 10\u201312","first-page":"809","article-title":"Cheetah: lean and fast secure {two-party} deep neural network inference","author":"Huang"},{"unstructured":"Dong Y, Lu WJ, Zheng Y, Wu H, Zhao D, Tan J, et al. Puma: secure inference of llama-7b in five minutes. arXiv:2307.12533. 2023.","key":"ref15"},{"key":"ref16","series-title":"2023 USENIX Annual Technical Conference (USENIX ATC 23); 2023 Jul 10\u201312","first-page":"17","article-title":"{SecretFlow-SPU}: a performant and {User-Friendly} framework for {Privacy-Preserving} machine learning","author":"Ma"},{"unstructured":"Jiang W, Song X, Hong S, Zhang H, Liu W, Zhao B, et al. Spin: an efficient secure computation framework with GPU acceleration. arXiv:2402.02320. 2024.","key":"ref17"},{"unstructured":"Peng S, Liu T, Tao T, Zhao D, Sheng H, Zhu H. EVA-S3PC: efficient, verifiable, accurate secure matrix multiplication protocol assembly and its application in regression. arXiv:2411.03404. 2024.","key":"ref18"},{"key":"ref19","series-title":"2018 IEEE Third International Conference on Data Science in Cyberspace (DSC); 2018 Jun 18\u201321","first-page":"652","article-title":"A survey on collaborative deep learning and privacy-preserving","author":"Zhang"},{"key":"ref20","first-page":"20","article-title":"A survey: privacy preservation techniques in data mining","volume":"119","author":"Vaghashia","year":"2015","journal-title":"Int J Comput Appl"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40537-018-0141-8","article-title":"Privacy preservation techniques in big data analytics: a survey","volume":"5","author":"Ram Mohan Rao","year":"2018","journal-title":"J Big Data"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"20170350","DOI":"10.1098\/rsta.2017.0350","article-title":"Machine learning and genomics: precision medicine versus patient privacy","volume":"376","author":"Azencott","year":"2018","journal-title":"Philos Trans R Soc A Mathem Phys Eng Sci"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"945","DOI":"10.1093\/jamia\/ocy017","article-title":"Distributed deep learning networks among institutions for medical imaging","volume":"25","author":"Chang","year":"2018","journal-title":"J Am Med Inform Associat"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"388","DOI":"10.1016\/j.procs.2018.01.136","article-title":"Security enhancement in healthcare cloud using machine learning","volume":"127","author":"Marwan","year":"2018","journal-title":"Proc Comput Sci"},{"key":"ref25","first-page":"200","article-title":"Developing high performance secure multi-party computation protocols in healthcare: a case study of patient risk stratification","volume":"2021","author":"Dong","year":"2021","journal-title":"AMIA Summ Translat Sci Proc"},{"key":"ref26","series-title":"2019 IEEE International Conference on Data Mining (ICDM); 2019 Nov 8\u201311","first-page":"1102","article-title":"A distributed fair machine learning framework with private demographic data protection","author":"Hu"},{"key":"ref27","series-title":"2021 IEEE 94th Vehicular Technology Conference (VTC2021-Fall); 2021 Sep 27\u2013Oct 28","first-page":"1","article-title":"Rapid network planning of temporary private 5G networks with unsupervised machine learning","author":"Bektas"},{"key":"ref28","series-title":"Proceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition; 2022 Jun 18\u201324","first-page":"4134","article-title":"Privacy-preserving online AutoML for domain-specific face detection","author":"Yan"},{"key":"ref29","series-title":"International Conference on Machine Learning","first-page":"4490","article-title":"TAPAS: tricks to accelerate (encrypted) prediction as a service","author":"Sanyal","year":"2018"},{"key":"ref30","first-page":"3819","article-title":"PrivEdge: from local to distributed private training and prediction","volume":"15","author":"Shamsabadi","year":"2020","journal-title":"IEEE Trans Inform Foren Secur"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1016\/j.comcom.2021.04.006","article-title":"PPAAS: privacy preservation as a service","volume":"173","author":"Chamikara","year":"2021","journal-title":"Comput Communicat"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"50","DOI":"10.3390\/cryptography9030050","article-title":"Efficient secure multi-party computation for multi-dimensional arithmetics and its applications","volume":"9","author":"Wu","year":"2025","journal-title":"Cryptography"},{"key":"ref33","series-title":"International Conference on Theory and Applications of Models of Computation","first-page":"1","article-title":"Differential privacy: a survey of results","author":"Dwork","year":"2008"},{"key":"ref34","series-title":"2015 IEEE Trustcom\/BigDataSE\/ISPA; 2015 Aug 20\u201322","first-page":"57","article-title":"Trusted execution environment: what it is, and what it is not","author":"Sabt"},{"unstructured":"Wu Z, Hou J, Diao Y, He B. Federated transformer: multi-party vertical federated learning on practical fuzzily linked data. arXiv:2410.17986. 2024.","key":"ref35"},{"unstructured":"Kone\u010dn\u1ef3 J, McMahan HB, Ramage D, Richt\u00e1rik P. Federated optimization: distributed machine learning for on-device intelligence. arXiv:1610.02527. 2016.","key":"ref36"},{"unstructured":"Kone\u010dn\u1ef3 J, McMahan HB, Yu FX, Richt\u00e1rik P, Suresh AT, Bacon D. Federated learning: strategies for improving communication efficiency. arXiv:1610.05492. 2016.","key":"ref37"},{"unstructured":"Zhao B, Mopuri KR, Bilen H. IDLG: improved deep leakage from gradients. arXiv:2001.02610. 2020.","key":"ref38"},{"key":"ref39","series-title":"2019 IEEE Symposium on Security and Privacy (SP); 2019 May 19\u201323","first-page":"691","article-title":"Exploiting unintended feature leakage in collaborative learning","author":"Melis"},{"year":"2019","author":"Zhu","journal-title":"Advances in neural information processing systems","key":"ref40"},{"unstructured":"Bettini C, Civitarese G, Presotto R. Personalized semi-supervised federated learning for human activity recognition. arXiv:2104.08094. 2021.","key":"ref41"},{"unstructured":"Samarati P, Sweeney L. Protecting privacy when disclosing information: k-anonymity and its enforcement through generalization and suppression [Internet]. Silicon Valley, CA, USA: SRI International, Massachusetts Institute of Technology; 1998 [cited 2025 Aug 12]. Available from: https:\/\/dataprivacylab.org\/dataprivacy\/projects\/kanonymity\/paper3.pdf.","key":"ref42"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1142\/S0218488502001648","article-title":"k-anonymity: a model for protecting privacy","volume":"10","author":"Sweeney","year":"2002","journal-title":"Int J Uncert Fuzz Knowl-Based Syst"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1145\/1217299.1217302","article-title":"l-diversity: privacy beyond k-anonymity","volume":"1","author":"Machanavajjhala","year":"2007","journal-title":"ACM Trans Knowl Disc Data"},{"key":"ref45","series-title":"2007 IEEE 23rd International Conference on Data Engineering; 2006 Apr 15\u20132007 Apr 20","first-page":"106","article-title":"t-closeness: privacy beyond k-anonymity and l-diversity","author":"Li"},{"key":"ref46","series-title":"Proceedings of the 2007 ACM SIGMOD International Conference on Management of Data; 2007 Jun 12\u201314","first-page":"689","article-title":"M-invariance: towards privacy preserving re-publication of dynamic datasets","author":"Xiao"},{"key":"ref47","series-title":"Theory of Cryptography Conference","first-page":"265","article-title":"Calibrating noise to sensitivity in private data analysis","author":"Dwork","year":"2006"},{"key":"ref48","series-title":"Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security; 2016 Oct 24\u201328","first-page":"308","article-title":"Deep learning with differential privacy","author":"Abadi"},{"key":"ref49","series-title":"Thirtieth AAAI Conference on Artificial Intelligence; 2016 Feb 12\u201317","first-page":"1309","article-title":"Differential privacy preservation for deep auto-encoders: an application of human behavior prediction","author":"Phan"},{"key":"ref50","series-title":"2017 IEEE International Conference on Data Mining (ICDM); 2017 Nov 18\u201321","first-page":"385","article-title":"Adaptive laplace mechanism: differential privacy preservation in deep learning","author":"Phan"},{"key":"ref51","doi-asserted-by":"crossref","first-page":"1681","DOI":"10.1007\/s10994-017-5656-2","article-title":"Preserving differential privacy in convolutional deep belief networks","volume":"106","author":"Phan","year":"2017","journal-title":"Mach Learn"},{"unstructured":"Papernot N, Abadi M, Erlingsson U, Goodfellow I, Talwar K. Semi-supervised knowledge transfer for deep learning from private training data. arXiv:1610.05755. 2016.","key":"ref52"},{"unstructured":"Papernot N, Song S, Mironov I, Raghunathan A, Talwar K, Erlingsson \u00da. Scalable private learning with pate. arXiv:1802.08908. 2018.","key":"ref53"},{"unstructured":"Xie L, Lin K, Wang S, Wang F, Zhou J. Differentially private generative adversarial network. arXiv:1802.06739. 2018.","key":"ref54"},{"key":"ref55","doi-asserted-by":"crossref","first-page":"1109","DOI":"10.1109\/TKDE.2018.2855136","article-title":"Differentially private mixture of generative neural networks","volume":"31","author":"Acs","year":"2018","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"ref56","article-title":"Deep learning with gaussian differential privacy","volume":"2020","author":"Bu","year":"2020","journal-title":"Harv Data Sci Rev"},{"key":"ref57","series-title":"International Conference on the Theory and Application of Cryptology and Information Security","first-page":"1","article-title":"MPC vs. SFE: unconditional and computational security","author":"Hirt","year":"2008"},{"key":"ref58","series-title":"European Symposium on Research in Computer Security","first-page":"1","article-title":"Practical covertly secure MPC for dishonest majority-or: breaking the SPDZ limits","author":"Damg\u00e5rd","year":"2013"},{"key":"ref59","series-title":"Proceedings of the Twenty-Second Annual ACM Symposium on Theory of Computing; 1990 May 14\u201316","first-page":"503","article-title":"The round complexity of secure protocols","author":"Beaver"},{"key":"ref60","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1109\/TDSC.2017.2679189","article-title":"Efficient and private scoring of decision trees, support vector machines and logistic regression models based on pre-computation","volume":"16","author":"De Cock","year":"2017","journal-title":"IEEE Trans Depend Sec Comput"},{"key":"ref61","series-title":"Annual International Cryptology Conference","first-page":"769","article-title":"SPDZ2k: efficient MPC mod 2k for dishonest majority","author":"Cramer","year":"2018"},{"key":"ref62","series-title":"Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security; 2016 Oct 24\u201328","first-page":"830","article-title":"MASCOT: faster malicious arithmetic secure computation with oblivious transfer","author":"Keller"},{"key":"ref63","series-title":"Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security; 2020 Nov 9\u201313","first-page":"1575","article-title":"MP-SPDZ: a versatile framework for multi-party computation","author":"Keller"},{"doi-asserted-by":"crossref","unstructured":"Demmler D, Schneider T, Zohner M. ABY-A framework for efficient mixed-protocol secure two-party computation [Internet]. In: NDSS; 2015 [cited 2025 Aug 12]. Available from: https:\/\/encrypto.de\/papers\/DSZ15.pdf.","key":"ref64","DOI":"10.14722\/ndss.2015.23113"},{"key":"ref65","series-title":"Cryptographers\u2019 Track at the RSA Conference","first-page":"473","article-title":"EPIC: efficient private image classification (or: learning from the masters)","author":"Makri","year":"2019"},{"key":"ref66","series-title":"Proceedings of the 2019 ACM SIGSAC Conference on Cloud Computing Security Workshop; 2019 Nov 11","first-page":"81","article-title":"ASTRA: high throughput 3pc over rings with application to secure prediction","author":"Chaudhari"},{"key":"ref67","series-title":"Proceedings of the 15th International Conference on Availability, Reliability and Security; 2020 Aug 25\u201328","first-page":"1","article-title":"MP2ML: a mixed-protocol machine learning framework for private inference","author":"Boemer"},{"key":"ref68","series-title":"2019 IEEE International Conference on Big Data (Big Data); 2019 Dec 9\u201312","first-page":"1312","article-title":"Securegbm: secure multi-party gradient boosting","author":"Feng"},{"key":"ref69","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition; 2021 Jun 20\u201325","first-page":"3300","article-title":"Mlcapsule: guarded offline deployment of machine learning as a service","author":"Hanzlik"},{"key":"ref70","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s42400-020-00057-3","article-title":"Lightning-fast and privacy-preserving outsourced computation in the cloud","volume":"3","author":"Liu","year":"2020","journal-title":"Cybersecurity"},{"key":"ref71","doi-asserted-by":"crossref","first-page":"29344","DOI":"10.1109\/ACCESS.2019.2901219","article-title":"Mscryptonet: multi-scheme privacy-preserving deep learning in cloud computing","volume":"7","author":"Kwabena","year":"2019","journal-title":"IEEE Access"},{"key":"ref72","series-title":"International Conference on Machine Learning","first-page":"201","article-title":"Cryptonets: applying neural networks to encrypted data with high throughput and accuracy","author":"Gilad-Bachrach","year":"2016"},{"unstructured":"Xie P, Bilenko M, Finley T, Gilad-Bachrach R, Lauter K, Naehrig M. Crypto-nets: neural networks over encrypted data. arXiv:1412.6181. 2014. doi:10.48550\/arxiv.1412.6181.","key":"ref73"},{"unstructured":"Hesamifard E, Takabi H, Ghasemi M. Cryptodl: deep neural networks over encrypted data. arXiv:1711.05189. 2017. doi:10.48550\/arxiv.1711.05189.","key":"ref74"},{"unstructured":"Chabanne H, De Wargny A, Milgram J, Morel C, Prouff E. Privacy-preserving classification on deep neural network. Cryptology ePrint Archive 2017 [Internet]. [cited 2025 Aug 12]. Available from: https:\/\/eprint.iacr.org\/2017\/035.","key":"ref75"},{"key":"ref76","doi-asserted-by":"crossref","first-page":"411","DOI":"10.3390\/electronics8040411","article-title":"Privacy-preserving distributed deep learning via homomorphic re-encryption","volume":"8","author":"Tang","year":"2019","journal-title":"Electronics"},{"key":"ref77","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/j.future.2017.02.006","article-title":"Multi-key privacy-preserving deep learning in cloud computing","volume":"74","author":"Li","year":"2017","journal-title":"Futu Gener Comput Syst"},{"unstructured":"Gu Z, Huang H, Zhang J, Su D, Lamba A, Pendarakis D, et al. Securing input data of deep learning inference systems via partitioned enclave execution. arXiv:1807.00969. 2018.","key":"ref78"},{"unstructured":"Hunt T, Song C, Shokri R, Shmatikov V, Witchel E. Chiron: privacy-preserving machine learning as a service. arXiv:1803.05961. 2018.","key":"ref79"},{"key":"ref80","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3231594","article-title":"Ryoan: a distributed sandbox for untrusted computation on secret data","volume":"35","author":"Hunt","year":"2018","journal-title":"ACM Trans Comput Syst"},{"unstructured":"Tramer F, Boneh D. Slalom: fast, verifiable and private execution of neural networks in trusted hardware. arXiv:1806.03287. 2018.","key":"ref81"},{"key":"ref82","first-page":"169","article-title":"On data banks and privacy homomorphisms","volume":"4","author":"Rivest","year":"1978","journal-title":"Foundat Secur Comput"},{"key":"ref83","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3214303","article-title":"A survey on homomorphic encryption schemes: theory and implementation","volume":"51","author":"Acar","year":"2018","journal-title":"ACM Comput Surv"},{"key":"ref84","series-title":"Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation; 2019 Jun 22\u201326","first-page":"142","article-title":"CHET: an optimizing compiler for fully-homomorphic neural-network inferencing","author":"Dathathri"},{"key":"ref85","series-title":"International Conference on Information Security and Cryptology","first-page":"1","article-title":"ML confidential: machine learning on encrypted data","author":"Graepel","year":"2012"},{"key":"ref86","series-title":"29th Annual Conference on Neural Information Processing Systems (NIPS); 2016 Dec 5\u201310","first-page":"1","article-title":"Privacy preserving multi-party machine learning with homomorphic encryption","author":"Takabi"},{"key":"ref87","series-title":"Annual International Cryptology Conference","first-page":"483","article-title":"Fast homomorphic evaluation of deep discretized neural networks","author":"Bourse","year":"2018"},{"unstructured":"Han K, Hong S, Cheon JH, Park D. Efficient logistic regression on large encrypted data. Cryptology ePrint Archive 2018 [Internet]. [cited 2025 Aug 12]. Available from: https:\/\/eprint.iacr.org\/2018\/662.","key":"ref88"},{"key":"ref89","series-title":"Proceedings of the 16th ACM International Conference on Computing Frontiers; 2019 Apr 30\u2013May 2","first-page":"3","article-title":"nGraph-HE: a graph compiler for deep learning on homomorphically encrypted data","author":"Boemer"},{"unstructured":"Folkerts L, Gouert C, Tsoutsos NG. REDsec: running encrypted discretized neural networks in seconds. Cryptology ePrint Archive 2021 [Internet]. [cited 2025 Aug 12]. Available from: https:\/\/eprint.iacr.org\/2021\/1100.","key":"ref90"},{"key":"ref91","series-title":"33rd USENIX Security Symposium (USENIX Security 24); 2024 Aug 14\u201316","first-page":"2173","article-title":"{AutoFHE}: automated adaption of {CNNs} for efficient evaluation over {FHE}","author":"Ao"},{"key":"ref92","series-title":"Proceedings of the 30th ACM International Conference on Multimedia; 2022 Oct 10\u201314","first-page":"1474","article-title":"Keyword spotting in the homomorphic encrypted domain using deep complex-valued CNN","author":"Zheng"},{"unstructured":"Zimerman I, Baruch M, Drucker N, Ezov G, Soceanu O, Wolf L. Converting transformers to polynomial form for secure inference over homomorphic encryption. arXiv:2311.08610. 2023.","key":"ref93"},{"key":"ref94","series-title":"SECRYPT 2020, 17th International Joint Conference on Security and Cryptography; 2020 Jul 8\u201310","first-page":"397","article-title":"ProteiNN: privacy-preserving one-to-many Neural Network classifications","author":"Bozdemir"},{"key":"ref95","doi-asserted-by":"crossref","first-page":"1333","DOI":"10.1109\/TIFS.2017.2787987","article-title":"Privacy-preserving deep learning via additively homomorphic encryption","volume":"13","author":"Phong","year":"2017","journal-title":"IEEE Trans Inform Foren Secur"},{"key":"ref96","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3394658","article-title":"Homomorphic encryption for machine learning in medicine and bioinformatics","volume":"53","author":"Wood","year":"2020","journal-title":"ACM Comput Surv"},{"key":"ref97","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1016\/j.ins.2020.03.041","article-title":"Privacy preservation for machine learning training and classification based on homomorphic encryption schemes","volume":"526","author":"Li","year":"2020","journal-title":"Inform Sci"},{"key":"ref98","doi-asserted-by":"crossref","first-page":"3910250","DOI":"10.1155\/2020\/3910250","article-title":"Applying deep neural networks over homomorphic encrypted medical data","volume":"2020","author":"Vizitiu","year":"2020","journal-title":"Comput Math Methods Med"},{"key":"ref99","series-title":"WAHC 2020\u20148th Workshop on Encrypted Computing & Applied Homomorphic Cryptography; 2020 Dec 15","first-page":"64","article-title":"Lattigo: a multiparty homomorphic encryption library in go","author":"Mouchet"},{"key":"ref100","series-title":"Proceedings of the Forty-first Annual ACM Symposium on Theory of Computing; 2009 May 31\u2013Jun 2","first-page":"169","article-title":"Fully homomorphic encryption using ideal lattices","author":"Gentry"},{"key":"ref101","series-title":"IMA International Conference on Cryptography and Coding","first-page":"45","article-title":"Improved security for a ring-based fully homomorphic encryption scheme","author":"Bos","year":"2013"},{"key":"ref102","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1016\/j.ins.2018.12.015","article-title":"Non-interactive privacy-preserving neural network prediction","volume":"481","author":"Ma","year":"2019","journal-title":"Inform Sci"},{"key":"ref103","series-title":"Annual International Conference on the Theory and Applications of Cryptographic Techniques","first-page":"457","article-title":"Fuzzy identity-based encryption","author":"Sahai","year":"2005"},{"key":"ref104","series-title":"Theory of Cryptography Conference","first-page":"253","article-title":"Functional encryption: definitions and challenges","author":"Boneh","year":"2011"},{"key":"ref105","doi-asserted-by":"crossref","first-page":"7436","DOI":"10.1109\/JIOT.2023.3338220","article-title":"Privacy-preserving machine learning using functional encryption: opportunities and challenges","volume":"11","author":"Panzade","year":"2023","journal-title":"IEEE Internet Things J"},{"key":"ref106","series-title":"23rd Annul Symposium on Foundations of Computer Science (sfcs 1982); 1982 Nov 3\u20135","first-page":"160","article-title":"Protocols for secure computations","author":"Yao"},{"key":"ref107","first-page":"110","article-title":"Secure multi-party computation","volume":"78","author":"Goldreich","year":"1998","journal-title":"Manuscript Preliminary Version"},{"key":"ref108","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1016\/j.ins.2018.10.024","article-title":"Secure multi-party computation: theory, practice and applications","volume":"476","author":"Zhao","year":"2019","journal-title":"Inform Sci"},{"unstructured":"Thomas R, Zahran L, Choi E, Potti A, Goldblum M, Pal A. An attack to break permutation-based private third-party inference schemes for LLMs. arXiv:2505.18332. 2025.","key":"ref109"},{"key":"ref110","series-title":"Annual International Cryptology Conference","first-page":"167","article-title":"The TinyTable protocol for 2-party secure computation, or: gate-scrambling revisited","author":"Damg\u00e5rd","year":"2017"},{"key":"ref111","series-title":"Annual International Cryptology Conference","first-page":"365","article-title":"Optimizing authenticated garbling for faster secure two-party computation","author":"Katz","year":"2018"},{"key":"ref112","series-title":"Annual International Cryptology Conference","first-page":"34","article-title":"Fast large-scale honest-majority MPC for malicious adversaries","author":"Chida","year":"2018"},{"key":"ref113","first-page":"351","author":"Ben-Or","year":"2019","journal-title":"Providing sound foundations for cryptography: on the work of shafi goldwasser and silvio micali"},{"key":"ref114","series-title":"International Conference on Coding and Cryptology","first-page":"11","article-title":"Secret-sharing schemes: a survey","author":"Beimel","year":"2011"},{"key":"ref115","series-title":"Proceedings of the Nineteenth Annual ACM Symposium on Theory of Computing","first-page":"210","article-title":"Zero knowledge proofs of identity","author":"Fiege","year":"1987"},{"key":"ref116","first-page":"1749","article-title":"From keys to databases\u2014real-world applications of secure multi-party computation","volume":"61","author":"Archer","year":"2018","journal-title":"Comput J"},{"key":"ref117","series-title":"International Conference on Financial Cryptography and Data Security","first-page":"325","article-title":"Secure multiparty computation goes live","author":"Bogetoft","year":"2009"},{"year":"2015","author":"Kairouz","journal-title":"Advances in neural information processing systems","key":"ref118"},{"key":"ref119","doi-asserted-by":"crossref","first-page":"1540","DOI":"10.3390\/s21041540","article-title":"Using secure multi-party computation to protect privacy on a permissioned blockchain","volume":"21","author":"Zhou","year":"2021","journal-title":"Sensors"},{"doi-asserted-by":"crossref","unstructured":"Harth-Kitzerow C, Suresh A, Wang Y, Yalame H, Carle G, Annavaram M. High-throughput secure multiparty computation with an honest majority in various network settings. arXiv:2206.03776. 2025.","key":"ref120","DOI":"10.56553\/popets-2025-0015"},{"key":"ref121","series-title":"Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; 2017 Aug 13\u201317","first-page":"1145","article-title":"Adversary resistant deep neural networks with an application to malware detection","author":"Wang"},{"key":"ref122","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1016\/j.knosys.2019.05.007","article-title":"Adversary resistant deep neural networks via advanced feature nullification","volume":"179","author":"Han","year":"2019","journal-title":"Knowl Based Syst"},{"unstructured":"Guo C, Rana M, Cisse M, Van Der Maaten L. Countering adversarial images using input transformations. arXiv:1711.00117. 2017. doi:10.48550\/arxiv.1711.00117.","key":"ref123"},{"unstructured":"Shaham U, Garritano J, Yamada Y, Weinberger E, Cloninger A, Cheng X, et al. Defending against adversarial images using basis functions transformations. arXiv:1803.10840. 2018.","key":"ref124"},{"key":"ref125","series-title":"Proceedings of the 25th International Conference on Machine Learning; 2008 Jul 5\u20139","first-page":"1096","article-title":"Extracting and composing robust features with denoising autoencoders","author":"Vincent"},{"key":"ref126","series-title":"2020 International Joint Conference on Neural Networks (IJCNN); 2020 Jul 19\u201324","first-page":"1","article-title":"Dapas: denoising autoencoder to prevent adversarial attack in semantic segmentation","author":"Cho"},{"key":"ref127","series-title":"Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition; 2018 Jun 18\u201323","first-page":"1778","article-title":"Defense against adversarial attacks using high-level representation guided denoiser","author":"Liao"},{"key":"ref128","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1109\/MSP.2012.2211477","article-title":"The mnist database of handwritten digit images for machine learning research [best of the web]","volume":"29","author":"Deng","year":"2012","journal-title":"IEEE Signal Process Magaz"},{"unstructured":"Athalye A, Carlini N. On the robustness of the CVPR 2018 white-box adversarial example defenses. arXiv:1804.03286. 2018.","key":"ref129"},{"year":"2018","author":"Song","journal-title":"Advances in neural information processing systems","key":"ref130"},{"key":"ref131","series-title":"2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS); 2017 Jun 5\u20138","first-page":"1442","article-title":"Private, yet practical, multiparty deep learning","author":"Zhang"},{"key":"ref132","series-title":"ICC 2019\u20142019 IEEE International Conference on Communications (ICC); 2019 May 20\u201324","first-page":"1","article-title":"Towards efficient and privacy-preserving federated deep learning","author":"Hao"},{"key":"ref133","series-title":"Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security; 2015 Oct 12\u201316","first-page":"1310","article-title":"Privacy-preserving deep learning","author":"Shokri"},{"key":"ref134","doi-asserted-by":"crossref","first-page":"3003","DOI":"10.1109\/TIFS.2019.2911169","article-title":"Privacy-preserving deep learning via weight transmission","volume":"14","author":"Phong","year":"2019","journal-title":"IEEE Transact Inform Foren Secur"},{"key":"ref135","series-title":"2019 IEEE International Conference on Big Data (Big Data); 2019 Dec 9\u201312","first-page":"2597","article-title":"Measure contribution of participants in federated learning","author":"Wang"},{"key":"ref136","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3339474","article-title":"Federated machine learning: concept and applications","volume":"10","author":"Yang","year":"2019","journal-title":"ACM Trans Intell Syst Technol"},{"key":"ref137","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1038\/s42256-020-0186-1","article-title":"Secure, privacy-preserving and federated machine learning in medical imaging","volume":"2","author":"Kaissis","year":"2020","journal-title":"Nat Mach Intell"},{"key":"ref138","doi-asserted-by":"crossref","first-page":"102402","DOI":"10.1016\/j.cose.2021.102402","article-title":"Privacy preservation in federated learning: an insightful survey from the GDPR perspective","volume":"110","author":"Truong","year":"2021","journal-title":"Comput Secur"},{"key":"ref139","doi-asserted-by":"crossref","first-page":"646","DOI":"10.1109\/TDSC.2016.2604383","article-title":"Privacy leakage of location sharing in mobile social networks: attacks and defense","volume":"15","author":"Li","year":"2016","journal-title":"IEEE Trans Depend Secur Comput"},{"unstructured":"Bellet A, Guerraoui R, Taziki M, Tommasi M. Fast and differentially private algorithms for decentralized collaborative machine learning [Ph.D. thesis]. Lille, France: INRIA Lille; 2017.","key":"ref140"},{"key":"ref141","first-page":"509","author":"Vanhaesebrouck","year":"2017","journal-title":"Artificial intelligence and statistics"},{"year":"2017","author":"Jiang","journal-title":"Advances in neural information processing systems","key":"ref142"},{"key":"ref143","series-title":"2021 IEEE International Symposium on High-Performance Computer Architecture (HPCA)","first-page":"26","article-title":"Cheetah: optimizing and accelerating homomorphic encryption for private inference","author":"Reagen"},{"key":"ref144","series-title":"2020 20th IEEE\/ACM International Symposium on Cluster, Cloud and Internet Computing (CCGRID); 2020 May 11\u201314","first-page":"410","article-title":"Two-phase multi-party computation enabled privacy-preserving federated learning","author":"Kanagavelu"},{"key":"ref145","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1038\/s41746-024-01293-4","article-title":"Privacy-friendly evaluation of patient data with secure multiparty computation in a European pilot study","volume":"7","author":"Ballhausen","year":"2024","journal-title":"npj Digital Med"},{"key":"ref146","doi-asserted-by":"crossref","first-page":"13061","DOI":"10.1038\/s41598-025-95858-2","article-title":"Federated learning with differential privacy for breast cancer diagnosis enabling secure data sharing and model integrity","volume":"15","author":"Shukla","year":"2025","journal-title":"Sci Rep"},{"key":"ref147","series-title":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management; 2024 Oct 21\u201325","first-page":"1473","article-title":"Collaborative fraud detection on large scale graph using secure multi-party computation","author":"Liu"},{"unstructured":"Claus B, John A, John A. Federated learning for collaborative fraud detection in financial networks: addressing data privacy concerns. ResearchGate; 2025 [Internet]. [cited 2025 Aug 12]. Available from: https:\/\/www.researchgate.net\/profile\/Ada-John\/publication\/390236470_Federated_Learning_for_Collaborative_Fraud_Detection_in_Financial_Networks_Addressing _Data_Privacy_Concerns\/links\/67e56ad3a43a11173bea94b8\/Federated-Learning-for-Collaborative-Fraud-Detection-in-Financial-Networks-Addressing-Data-Privacy-Concerns.pdf.","key":"ref148"},{"key":"ref149","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1038\/nbt.4108","article-title":"Secure genome-wide association analysis using multiparty computation","volume":"36","author":"Cho","year":"2018","journal-title":"Nat Biotechnol"},{"key":"ref150","doi-asserted-by":"crossref","first-page":"537","DOI":"10.1186\/s12859-018-2541-3","article-title":"Towards practical privacy-preserving genome-wide association study","volume":"19","author":"Bonte","year":"2018","journal-title":"BMC Bioinform"},{"key":"ref151","doi-asserted-by":"crossref","first-page":"119915","DOI":"10.1016\/j.apenergy.2022.119915","article-title":"Privacy-preserving federated learning for residential short-term load forecasting","volume":"326","author":"Fern\u00e1ndez","year":"2022","journal-title":"Appl Energy"},{"key":"ref152","series-title":"33rd USENIX Security Symposium (USENIX Security 24)","first-page":"2191","article-title":"Fast and private inference of deep neural networks by co-designing activation functions","author":"Diaa","year":"2024"},{"key":"ref153","doi-asserted-by":"crossref","first-page":"985","DOI":"10.3390\/electronics14050985","article-title":"Communication efficient secure three-party computation using lookup tables for RNN inference","volume":"14","author":"Wu","year":"2025","journal-title":"Electronics"},{"unstructured":"Thomas R, Zahran L, Choi E, Potti A, Goldblum M, Pal A. Cascade: token-sharded private LLM inference. arXiv:2507.05228. 2025.","key":"ref154"},{"unstructured":"Jagielski M, Escudero D, Rachuri R, Scholl P. Covert attacks on machine learning training in passively secure MPC. arXiv:2505.17092. 2025.","key":"ref155"},{"year":"2018","author":"Hayes","journal-title":"Advances in neural information processing systems","key":"ref156"},{"key":"ref157","series-title":"2024 Workshop on Fault Detection and Tolerance in Cryptography (FDTC); 2024 Sep 4","first-page":"53","article-title":"Faultygarble: fault attack on secure multiparty neural network inference","author":"Hashemi"},{"key":"ref158","series-title":"2025 IEEE Symposium on Security and Privacy (SP); 2025 May 12\u201315","first-page":"2491","article-title":"Rushing at SPDZ: on the practical security of malicious MPC implementations","author":"Kyster"},{"key":"ref159","series-title":"2016 International Conference on Computational Science and Computational Intelligence (CSCI); 2016 Dec 15\u201317","first-page":"192","article-title":"A collaborative privacy-preserving deep learning system in distributed mobile environment","author":"Liu"},{"key":"ref160","series-title":"2015 IEEE 17th International Conference on High Performance Computing and Communications, 2015 IEEE 7th International Symposium on Cyberspace Safety and Security, and 2015 IEEE 12th International Conference on Embedded Software and Systems; 2015 Aug 24\u201326","first-page":"1791","article-title":"Privacy preserving back-propagation based on BGV on cloud","author":"Bu"},{"key":"ref161","doi-asserted-by":"crossref","first-page":"1368905","DOI":"10.1155\/2019\/1368905","article-title":"Secure multiparty computation and trusted hardware: examining adoption challenges and opportunities","volume":"2019","author":"Choi","year":"2019","journal-title":"Secur Commun Netw"},{"key":"ref162","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1007\/s10207-024-00939-4","article-title":"Challenges and future research directions in secure multi-party computation for resource-constrained devices and large-scale computations","volume":"24","author":"Gamiz","year":"2025","journal-title":"Int J Inf Secur"},{"key":"ref163","doi-asserted-by":"crossref","first-page":"53881","DOI":"10.1109\/ACCESS.2024.3388992","article-title":"Secure multi-party computation for machine learning: a survey","volume":"12","author":"Zhou","year":"2024","journal-title":"IEEE Access"},{"key":"ref164","series-title":"Proceedings of the 2001 Workshop on New Security Paradigms; 2001 Sep 11\u201313","first-page":"13","article-title":"Secure multi-party computation problems and their applications: a review and open problems","author":"Du"},{"key":"ref165","doi-asserted-by":"crossref","first-page":"807","DOI":"10.1007\/s12652-015-0299-2","article-title":"A brief survey on secure multi-party computing in the presence of rational parties","volume":"6","author":"Wang","year":"2015","journal-title":"J Amb Intell Human Comput"},{"unstructured":"Li Y, Zhou X, Wang Y, Qian L, Zhao J. Private transformer inference in MLaaS: a survey. arXiv:2505.10315. 2025.","key":"ref166"},{"unstructured":"Li Y, Zhou X, Wang Y, Qian L, Zhao JA. A survey on private transformer inference. arXiv:2412.08145. 2024.","key":"ref167"},{"key":"ref168","series-title":"International Symposium on Parallel and Distributed Processing with Applications; 2010 Sep 6\u20139","first-page":"200","article-title":"Multi-party k-means clustering with privacy consideration","author":"Yu"},{"key":"ref169","series-title":"Proceedings of the Second International Conference on Security and Cryptography; 2007 Jul 28\u201313","first-page":"381","article-title":"Privacy preserving k-means clustering in multi-party environment","author":"Samet"},{"unstructured":"Ram\u00edrez DH, Au\u00f1\u00f3n J. Privacy preserving k-means clustering: a secure multi-party computation approach. arXiv:2009.10453. 2020.","key":"ref170"},{"key":"ref171","series-title":"2019 IEEE Symposium on Security and Privacy (SP); 2019 May 19\u201323","first-page":"1102","article-title":"New primitives for actively-secure MPC over rings with applications to private machine learning","author":"Damg\u00e5rd"},{"doi-asserted-by":"crossref","unstructured":"Chaudhari H, Rachuri R, Suresh A. Trident: efficient 4pc framework for privacy preserving machine learning. arXiv:1912.02631. 2019.","key":"ref172","DOI":"10.14722\/ndss.2020.23005"},{"author":"Mugunthan","article-title":"Smpai: secure multi-party computation for federated learning","series-title":"33rd Conference on Neural Information Processing Systems (NeurIPS 2019); 2019 Dec 8\u201314","key":"ref173"},{"key":"ref174","series-title":"2020 IEEE 19th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom); 2020 Dec 29\u20132021 Jan 1","first-page":"707","article-title":"Multi-party private set intersection in vertical federated learning","author":"Lu"},{"key":"ref175","doi-asserted-by":"crossref","first-page":"6178","DOI":"10.1109\/JIOT.2020.3022911","article-title":"Privacy-preserving federated learning framework based on chained secure multiparty computing","volume":"8","author":"Li","year":"2020","journal-title":"IEEE Internet Things J"},{"key":"ref176","series-title":"Proceedings of the ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; 2003 Aug 24\u201327","first-page":"206","article-title":"Privacy-preserving k-means clustering over vertically partitioned data","author":"Vaidya"},{"key":"ref177","series-title":"Proceedings of the Eleventh ACM Conference on Recommender Systems; 2017 Aug 27\u201331","first-page":"89","article-title":"Secure multi-party protocols for item-based collaborative filtering","author":"Shmueli"},{"key":"ref178","series-title":"International Conference on Machine Learning","first-page":"6326","article-title":"Privacy-preserving feature selection with secure multiparty computation","author":"Li","year":"2021"},{"key":"ref179","series-title":"30th USENIX Security Symposium (USENIX Security 21); 2021 Aug 11\u201313","first-page":"2723","article-title":"Cerebro: a platform for {Multi-Party} cryptographic collaborative learning","author":"Zheng"},{"key":"ref180","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2633600","article-title":"(Leveled) fully homomorphic encryption without bootstrapping","volume":"6","author":"Brakerski","year":"2014","journal-title":"ACM Trans Comput Theory"},{"key":"ref181","series-title":"Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security; 2016 Oct 24\u201328","first-page":"578","article-title":"Optimizing semi-honest secure multiparty computation for the Internet","author":"Ben-Efraim"},{"key":"ref182","series-title":"Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security; 2016 Oct 24\u201328","first-page":"805","article-title":"High-throughput semi-honest secure three-party computation with an honest majority","author":"Araki"},{"key":"ref183","series-title":"Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security; 2018 Oct 15\u201319","first-page":"35","article-title":"ABY3: a mixed protocol framework for machine learning","author":"Mohassel"},{"unstructured":"Wagh S, Gupta D, Chandran N. SecureNN: efficient and private neural network training. Cryptology ePrint Archive 2018 [Internet]. [cited 2025 Aug 12]. Available from: https:\/\/eprint.iacr.org\/2018\/442.","key":"ref184"},{"key":"ref185","series-title":"International Conference on Financial Cryptography and Data Security","first-page":"369","article-title":"Communication-efficient (client-aided) secure two-party protocols and its application","author":"Ohata","year":"2020"},{"unstructured":"Carpov S, Deforth K, Gama N, Georgieva M, Jetchev D, Katz J, et al. Manticore: efficient framework for scalable secure multiparty computation protocols. Cryptology ePrint Archive 2021 [Internet]. [cited 2025 Aug 12]. Available from: https:\/\/eprint.iacr.org\/2021\/200.","key":"ref186"},{"key":"ref187","series-title":"30th USENIX Security Symposium (USENIX Security 21); 2021 Aug 11\u201313","first-page":"2183","article-title":"Fantastic four: {Honest-Majority}{Four-Party} secure computation with malicious security","author":"Dalskov"},{"key":"ref188","series-title":"International Conference on Financial Cryptography and Data Security","first-page":"249","article-title":"Rabbit: efficient comparison for secure multi-party computation","author":"Makri","year":"2021"},{"key":"ref189","series-title":"Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security; 2021 Nov 15\u201319","first-page":"610","article-title":"Secure graph analysis at scale","author":"Araki"},{"key":"ref190","doi-asserted-by":"crossref","first-page":"103552","DOI":"10.1016\/j.csi.2021.103552","article-title":"Generic server-aided secure multi-party computation in cloud computing","volume":"79","author":"Wu","year":"2022","journal-title":"Comput Stand Interf"},{"key":"ref191","series-title":"Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security; 2022 Nov 7\u201311","first-page":"3331","article-title":"Poster: efficient three-party shuffling using precomputation","author":"Br\u00fcggemann"},{"key":"ref192","first-page":"2820","article-title":"Efficient server-aided secure two-party computation in heterogeneous mobile cloud computing","volume":"18","author":"Wu","year":"2020","journal-title":"IEEE Trans Depend Secure Comput"},{"key":"ref193","first-page":"933","author":"Rajkumar","year":"2012","journal-title":"Artificial intelligence and statistics"},{"key":"ref194","series-title":"2017 IEEE 10th International Conference on Cloud Computing (CLOUD); 2017 Jun 25\u201330","first-page":"342","article-title":"Privacy-preserving multi-party analytics over arbitrarily partitioned data","author":"Mehnaz"},{"key":"ref195","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1016\/j.ins.2018.05.005","article-title":"Privacy preserving multi-party computation delegation for deep learning in cloud computing","volume":"459","author":"Ma","year":"2018","journal-title":"Inform Sci"},{"key":"ref196","series-title":"2019 IEEE European Symposium on Security and Privacy (EuroS&P); 2019 Jun 17\u201319","first-page":"496","article-title":"EzPC: programmable and efficient secure two-party computation for machine learning","author":"Chandran"},{"key":"ref197","series-title":"Proceedings of the 2020 Workshop on Privacy-Preserving Machine Learning in Practice; 2020 Nov 9","first-page":"47","article-title":"Faster secure multiparty computation of adaptive gradient descent","author":"Lu"},{"doi-asserted-by":"crossref","unstructured":"Patra A, Suresh A. BLAZE: blazing fast privacy-preserving machine learning. arXiv:2005.09042. 2020.","key":"ref198","DOI":"10.14722\/ndss.2020.24202"},{"unstructured":"Byali M, Chaudhari H, Patra A, Suresh A. FLASH: fast and robust framework for privacy-preserving machine learning. Cryptology ePrint Archive 2019 [Internet]. [cited 2025 Aug 12]. Available from: https:\/\/eprint.iacr.org\/2019\/1365.","key":"ref199"},{"unstructured":"Aggarwal A, Carlson TE, Shokri R, Tople S. Soteria: in search of efficient neural networks for private inference. arXiv:2007.12934. 2020.","key":"ref200"},{"key":"ref201","doi-asserted-by":"crossref","first-page":"102754","DOI":"10.1016\/j.jnca.2020.102754","article-title":"Secure multiparty learning from the aggregation of locally trained models","volume":"167","author":"Ma","year":"2020","journal-title":"J Netw Comput Appl"},{"unstructured":"Chen M, Liu Y, Shen W, Shen Y, Tang P, Yang Q. Mechanism design for multi-party machine learning. arXiv:2001.08996. 2020.","key":"ref202"},{"key":"ref203","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3639368","article-title":"Fairness-driven private collaborative machine learning","volume":"15","author":"Pessach","year":"2024","journal-title":"ACM Trans Intell Syst Technol"},{"key":"ref204","series-title":"30th USENIX Security Symposium (USENIX Security 21); 2021 Aug 11\u201313","first-page":"2651","article-title":"{SWIFT}: super-fast and robust {Privacy-Preserving} machine learning","author":"Koti"},{"key":"ref205","series-title":"2021 IEEE Symposium on Security and Privacy (SP); 2021 May 24\u201327","first-page":"1021","article-title":"CryptGPU: fast privacy-preserving machine learning on the GPU","author":"Tan"},{"unstructured":"Ge Z, Zhou Z, Guo D, Li Q. Practical two-party privacy-preserving neural network based on secret sharing. arXiv:2104.04709. 2021.","key":"ref206"},{"key":"ref207","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1109\/JSAIT.2021.3053220","article-title":"CodedPrivateML: a fast and privacy-preserving framework for distributed machine learning","volume":"2","author":"So","year":"2021","journal-title":"IEEE J Select Areas Inform Theory"},{"author":"Yuan","article-title":"Label private deep learning training based on secure multiparty computation and differential privacy","series-title":"NeurIPS 2021 Workshop Privacy in Machine Learning; 2021 Aug 15","key":"ref208"},{"doi-asserted-by":"crossref","unstructured":"Koti N, Patra A, Rachuri R, Suresh A. Tetrad: actively secure 4pc for secure training and inference. arXiv:2106.02850. 2021.","key":"ref209","DOI":"10.14722\/ndss.2022.24058"},{"key":"ref210","series-title":"31st USENIX Security Symposium (USENIX Security 22); 2022 Aug 10\u201312","first-page":"827","article-title":"Piranha: a {GPU} platform for secure computation","author":"Watson"},{"key":"ref211","series-title":"Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security; 2022 Nov 7\u201311","first-page":"995","article-title":"NFGen: automatic non-linear function evaluation code generator for general-purpose MPC platforms","author":"Fan"},{"key":"ref212","series-title":"Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security; 2017 Oct 30\u2013Nov 3","first-page":"619","article-title":"Oblivious neural network predictions via minionn transformations","author":"Liu"},{"key":"ref213","series-title":"27th USENIX Security Symposium (USENIX Security 18); 2018 Aug 15\u201317","first-page":"1651","article-title":"{GAZELLE}: a low latency framework for secure neural network inference","author":"Juvekar"},{"unstructured":"Dahl M, Mancuso J, Dupis Y, Decoste B, Giraud M, Livingstone I, et al. Private machine learning in tensorflow using secure computation. arXiv:1810.08130. 2018.","key":"ref214"},{"key":"ref215","series-title":"Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia Security; 2021 Jun 22\u201325","first-page":"63","article-title":"Banners: binarized neural networks with replicated secret sharing","author":"Ibarrondo"},{"key":"ref216","series-title":"Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security; 2020 Nov 9\u201313","first-page":"325","article-title":"CrypTFlow2: practical 2-party secure inference","author":"Rathee"},{"author":"Tillem","article-title":"SwaNN: switching among cryptographic tools for privacy-preserving neural network predictions","series-title":"SECRYPT 2020, 17th International Conference on Security and Cryptography; 2020 Jul 8\u201310","key":"ref217"},{"unstructured":"Nawaz M, Gulati A, Liu K, Agrawal V, Ananth P, Gupta T. Accelerating 2PC-based ML with limited trusted hardware. arXiv:2009.05566. 2020.","key":"ref218"},{"key":"ref219","series-title":"Proceedings of the 2020 Workshop on Privacy-Preserving Machine Learning in Practice; 2020 Nov 9","first-page":"27","article-title":"Delphi: a cryptographic inference system for neural networks","author":"Mishra"},{"key":"ref220","series-title":"2021 IEEE Symposium on Security and Privacy (SP); 2021 May 24\u201327","first-page":"1003","article-title":"SiRNN: a math library for secure RNN inference","author":"Rathee"},{"key":"ref221","series-title":"2022 IEEE Symposium on Security and Privacy (SP); 2022 May 22\u201326","first-page":"576","article-title":"Secfloat: accurate floating-point meets secure 2-party computation","author":"Rathee"},{"doi-asserted-by":"crossref","unstructured":"Gupta K, Kumaraswamy D, Chandran N, Gupta D. Llama: a low latency math library for secure inference. Cryptology ePrint Archive 2022 [Internet]. [cited 2025 Aug 12]. Available from: https:\/\/eprint.iacr.org\/2022\/793.","key":"ref222","DOI":"10.56553\/popets-2022-0109"},{"unstructured":"Li D, Shao R, Wang H, Guo H, Xing EP, Zhang H. Mpcformer: fast, performant and private transformer inference with MPC. arXiv:2211.01452. 2022.","key":"ref223"},{"doi-asserted-by":"crossref","unstructured":"Zhang Y, Chen D, Kundu S, Liu H, Peng R, Beerel PA. C2PI: an efficient crypto-clear two-party neural network private inference. arXiv:2304.13266. 2023.","key":"ref224","DOI":"10.1109\/DAC56929.2023.10247682"},{"key":"ref225","series-title":"2023 IEEE 8th European Symposium on Security and Privacy (EuroS&P); 2023 Jul 3\u20137","first-page":"392","article-title":"Privformer: privacy-preserving transformer with MPC","author":"Akimoto"},{"key":"ref226","series-title":"Proceedings of the ACM Web Conference 2023; 2023 Apr 30\u2013May 4","first-page":"2087","article-title":"Meteor: improved secure 3-party neural network inference with reducing online communication costs","author":"Dong"},{"key":"ref227","first-page":"78906","article-title":"Copriv: network\/protocol co-optimization for communication-efficient private inference","volume":"36","author":"Zeng","year":"2023","journal-title":"Adv Neur Inform Process Syst"},{"doi-asserted-by":"crossref","unstructured":"Islam M, Arora SS, Chatterjee R, Rindal P, Shirvanian M. Compact: approximating complex activation functions for secure computation. arXiv:2309.04664. 2023.","key":"ref228","DOI":"10.56553\/popets-2024-0065"},{"doi-asserted-by":"crossref","unstructured":"Luo J, Zhang Y, Zhang Z, Zhang J, Mu X, Wang H, et al. Secformer: towards fast and accurate privacy-preserving inference for large language models. arXiv:2401.00793. 2024.","key":"ref229","DOI":"10.18653\/v1\/2024.findings-acl.790"},{"key":"ref230","series-title":"European Conference on Computer Vision","first-page":"288","article-title":"CipherDM: secure three-party inference for diffusion model sampling","author":"Zhao","year":"2024"},{"key":"ref231","series-title":"ICC 2024-IEEE International Conference on Communications; 2024 Jun 9\u201313","first-page":"61","article-title":"Roger: a round optimized GPU-friendly secure inference framework","author":"Chen"},{"unstructured":"Zeng W, Xu T, Li M, Wang R. EQO: exploring ultra-efficient private inference with winograd-based protocol and quantization co-optimization. arXiv:2404.09404. 2024.","key":"ref232"},{"unstructured":"Xu T, Li M, Wang R. Hequant: marrying homomorphic encryption and quantization for communication-efficient private inference. arXiv:2401.15970. 2024.","key":"ref233"},{"key":"ref234","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1561\/3300000019","article-title":"A pragmatic introduction to secure multi-party computation","volume":"2","author":"Evans","year":"2018","journal-title":"Found Trends\u00ae Priv Secur"},{"key":"ref235","series-title":"33rd USENIX Security Symposium (USENIX Security 24)","first-page":"2227","article-title":"MD-ML: super fast privacy-preserving machine learning for malicious security with a dishonest majority","author":"Yuan","year":"2024"},{"unstructured":"Sulimany K, Vadlamani SK, Hamerly R, Iyengar P, Englund D. Quantum-secure multiparty deep learning. arXiv:2408.05629. 2024.","key":"ref236"},{"key":"ref237","series-title":"Proceedings of the 2012 ACM conference on Computer and Communications Security; 2012 Oct 16\u201318","first-page":"797","article-title":"Salus: a system for server-aided secure function evaluation","author":"Kamara"},{"key":"ref238","series-title":"Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security; 2020 Nov 9\u201313","first-page":"1033","article-title":"SNI-in-the-head: protecting MPC-in-the-head protocols against side-channel analysis","author":"Seker"},{"key":"ref239","series-title":"The Network and Distributed System Security (NDSS) Symposium; 2022 Apr 24\u201328","first-page":"1","article-title":"Hybrid trust multi-party computation with trusted execution environment","author":"Wu"},{"key":"ref240","series-title":"2015 IEEE Symposium on Security and Privacy; 2015 May 17\u201321","first-page":"640","article-title":"Controlled-channel attacks: deterministic side channels for untrusted operating systems","author":"Xu"},{"key":"ref241","series-title":"Advances in Cryptology-EUROCRYPT 2007: 26th Annual International Conference on the Theory and Applications of Cryptographic Techniques","first-page":"115","article-title":"Universally composable multi-party computation using tamper-proof hardware","author":"Katz","year":"2007"},{"key":"ref242","series-title":"Theory of Cryptography: 7th Theory of Cryptography Conference, TCC 2010","first-page":"308","article-title":"Founding cryptography on tamper-proof hardware tokens","author":"Goyal","year":"2010"},{"unstructured":"Zheng F, Chen C, Han Z, Zheng X. PermLLM: private inference of large language models within 3 seconds under WAN. arXiv:2405.18744. 2024.","key":"ref243"},{"key":"ref244","series-title":"2025 IEEE Symposium on Security and Privacy (SP); 2025 May 12\u201315","first-page":"2827","article-title":"Comet: accelerating private inference for large language model by predicting activation sparsity","author":"Yan"},{"key":"ref245","first-page":"5653","article-title":"Secure multiparty computation for machine learning in healthcare","volume":"12","author":"Raju","year":"2024","journal-title":"Int J Intell Syst Appl Eng"},{"doi-asserted-by":"crossref","unstructured":"Effendi F, Chattopadhyay A. Privacy-preserving graph-based machine learning with fully homomorphic encryption for collaborative anti-money laundering. arXiv: 2411.02926. 2024.","key":"ref246","DOI":"10.1007\/978-3-031-80408-3_6"},{"key":"ref247","doi-asserted-by":"crossref","first-page":"35193","DOI":"10.1109\/JIOT.2024.3434660","article-title":"Byzantine-robust and privacy-preserving federated learning with irregular participants","volume":"11","author":"Chen","year":"2024","journal-title":"IEEE Internet Things J"}],"container-title":["Computers, Materials & Continua"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/cdn.techscience.cn\/files\/cmc\/2025\/TSP_CMC-85-2\/TSP_CMC_68875\/TSP_CMC_68875.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T05:35:34Z","timestamp":1764826534000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.techscience.com\/cmc\/v85n2\/63848"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":247,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025]]},"published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.32604\/cmc.2025.068875","relation":{},"ISSN":["1546-2226"],"issn-type":[{"type":"electronic","value":"1546-2226"}],"subject":[],"published":{"date-parts":[[2025]]}}}