[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-504640-105":59,"doc-detail-504640-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","cryptotrain-fast-secure-training-on-encrypted-dataset","CryptoTrain: Fast Secure Training on Encrypted Dataset","","Secure training protects both data and model weights, but often creates substantial overhead. Traditional Fully Homomorphic Encryption (FHE) non-interactive training is heavily slowed by computationally demanding bootstrapping. CryptoTrain-B introduces a hybrid protocol combining FHE with Oblivious Transfer (OT) to handle linear and non-linear operations, removing the need for costly bootstrapping. To further cut overhead, CCMul-Precompute reduces expensive encrypted-encrypted multiplications, and correlated polynomial convolution minimizes redundant polynomial encodings. Integrated into CryptoTrain, experiments show about a 5.3× training time reduction versus prior methods.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/cryptotrain-fast-secure-training-on-encrypted-dataset/504640/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/cryptotrain-fast-secure-training-on-encrypted-dataset/504640.png","ImageObject",300,407,{"name":92,"@type":93},"awa","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-17","2026-10-03",true,{"@type":102,"interactionType":103,"userInteractionCount":19},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What is the main goal of CryptoTrain in the paper?","Question",{"text":112,"@type":113},"CryptoTrain aims to speed up secure training on encrypted datasets while protecting the confidentiality of both input data and model weights.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does CryptoTrain-B reduce the need for expensive bootstrapping?",{"text":117,"@type":113},"CryptoTrain-B uses a hybrid cryptographic protocol that combines FHE with Oblivious Transfer (OT): FHE handles linear operations and OT handles non-linear operations, eliminating costly bootstrapping.",{"name":119,"@type":110,"acceptedAnswer":120},"Which bottleneck do the authors identify during private training, and how do they address it?",{"text":121,"@type":113},"They identify ciphertext-ciphertext multiplication (CCMul) as a critical bottleneck. They propose CCMul-Precompute, which precomputes CCMul offline and uses the less resource-intensive ciphertext-plaintext multiplication during training.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},504640,1791652907,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":19,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":39,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":143,"read_time":46},3985747858093,"https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2","CryptoTrain: Fast Secure Training on Encrypted Dataset  \nJiaqi Xue  \n[jiaqi.xue@ucf.edu](jiaqi.xue@ucf.edu)[ ](jiaqi.xue@ucf.edu)University of Central Florida Orlando, Florida, USA  \nXueqiang Wang  \n[xueqiang.wang@ucf.edu](xueqiang.wang@ucf.edu)[ ](xueqiang.wang@ucf.edu)University of Central Florida Orlando, Florida, USA  \nYancheng Zhang  \n[yancheng.zhang@ucf.edu](yancheng.zhang@ucf.edu)[ ](yancheng.zhang@ucf.edu)University of Central Florida Orlando, Florida, USA  \nHao Zheng  \n[hao.zheng@ucf.edu](hao.zheng@ucf.edu)[ ](hao.zheng@ucf.edu)University of Central Florida Orlando, Florida, USA  \nYanshan Wang  \n[yanshan.wang@pitt.edu](yanshan.wang@pitt.edu)[ ](yanshan.wang@pitt.edu)University of Pittsburgh Pittsburgh, Pennsylvania, USA  \nQian Lou  \n[qian.lou@ucf.edu](qian.lou@ucf.edu)[ ](qian.lou@ucf.edu)University of Central Florida Orlando, Florida, USA  \narXiv :2409 . 16675v2 [ cs .CR] 26 Sep 2024  \nAbstract  \nSecure training, while protecting the confidentiality of both data and model weights, typically incurs significant training overhead. Traditional Fully Homomorphic Encryption (FHE)-based non-interactive training models are heavily burdened by computationally demanding bootstrapping. To develop an efficient secure training system, we established a foundational framework, CryptoTrain-B, utilizing a hybrid cryptographic protocol that merges FHE with Oblivious Transfer (OT) for handling linear and non-linear operations, respectively. This integration eliminates the need for costly bootstrapping. Although CryptoTrain-B sets a new baseline in performance, reducing its training overhead remains essential. We found that ciphertext-ciphertext multiplication (CCMul) is a critical bottleneck in operations involving encrypted inputs and models. Our solution, the CCMul-Precompute technique, involves precomputing CCMul offline and resorting to the less resource-intensive ciphertext-plaintext multiplication (CPMul) during private training. Furthermore, conventional polynomial convolution in FHE systems tends to encode irrelevant and redundant values into polynomial slots, necessitating additional polynomials and ciphertexts for input representation and leading to extra multiplications. Addressing this, we introduce correlated polynomial convolution, which encodes only related input values into polynomials, thus drastically reducing the number of computations and overheads. By integrating CCMul-Precompute and correlated polynomial convolution into CryptoTrain-B, we facilitate a rapid and efficient secure training framework, CryptoTrain. Extensive experiments demonstrate that CryptoTrain achieves a ∼ 5. 3× training time reduction compared to prior methods.  \nCCS Concepts  \n• Security and privacy → Human and societal aspects of security and privacy; • Computing methodologies → Machine learning.  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission [and/or a fee. Request permissions from permissions@acm.org](and/or a fee. Request permissions from permissions@acm.org).  \nLAMPS’24, October 14–18, 2024, Salt Lake City, UT, USA.  \n© 2024 Copyright held by the owner/author(s) . Publication rights licensed to ACM. ACM ISBN 979-8-4007-1209-8/24/10  \n[https://doi.org/10.1145/3689217.3690617](https://doi.org/10.1145/3689217.3690617)  \nKeywords  \nSecure training; Homomorphic encryption; Oblivious transfer  \nACM Reference Format:  \nJiaqi Xue, Yancheng Zhang, Yanshan Wang, Xueqiang Wang, Hao Zheng, and Qian Lou. 2024. CryptoTrain: Fast Secure Training on Encrypted Dataset. In Proceedings of","cbCaiaRXiZJcvUR6","https://ap.wps.com/l/cbCaiaRXiZJcvUR6","pdf",1205981,"English","# Abstract\n# CCS Concepts\n# Keywords\n# 1 Introduction","[{\"question\":\"What is the main goal of CryptoTrain in the paper?\",\"answer\":\"CryptoTrain aims to speed up secure training on encrypted datasets while protecting the confidentiality of both input data and model weights.\"},{\"question\":\"How does CryptoTrain-B reduce the need for expensive bootstrapping?\",\"answer\":\"CryptoTrain-B uses a hybrid cryptographic protocol that combines FHE with Oblivious Transfer (OT): FHE handles linear operations and OT handles non-linear operations, eliminating costly bootstrapping.\"},{\"question\":\"Which bottleneck do the authors identify during private training, and how do they address it?\",\"answer\":\"They identify ciphertext-ciphertext multiplication (CCMul) as a critical bottleneck. They propose CCMul-Precompute, which precomputes CCMul offline and uses the less resource-intensive ciphertext-plaintext multiplication during training.\"}]","CryptoTrain: Fast Secure Training on Encrypted Dataset | PDF",1791071478]