[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122717-en":3,"doc-seo-122717-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},122717,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","DPpack: An R Package for Differentially Private Statistical Analysis and Machine Learning","Differential privacy (DP) is a state-of-the-art framework that protects individuals when releasing aggregated statistics or building statistical and machine learning models from sensitive data. The work introduces the open-source R package DPpack, offering a broad toolkit for differentially private analysis. DPpack implements three mechanisms—Laplace, Gaussian, and exponential—and provides privacy-preserving descriptive statistics such as mean, variance, covariance, quantiles, histograms, and contingency tables. It also includes user-friendly implementations of logistic regression, SVM, and linear regression with differentially private hyperparameter tuning, and it outlines future extensions to additional DP techniques, modeling, and inference.","arXiv :2309 . 10965v1 [ stat .ML] 19 Sep 2023  \nGiddens and Liu  \nDPpack: An R Package for Differentially Private Statistical Analysis and Machine Learning  \nSpencer Giddens [sgiddens@nd.edu](sgiddens@nd.edu)  \nDepartment of Applied and Computational Mathematics and Statistics University of Notre Dame, Notre Dame, IN 46556, USA  \nFang Liu [fliu2@nd.edu](fliu2@nd.edu)  \nDepartment of Applied and Computational Mathematics and Statistics University of Notre Dame, Notre Dame, IN 46556, USA  \nAbstract  \nDifferential privacy (DP) is the state-of-the-art framework for guaranteeing privacy for individuals when releasing aggregated statistics or building statistical/machine learning models from data. We develop the open-source R package DPpack that provides a large toolkit of differentially private analysis. The current version of DPpack implements three popular mechanisms for ensuring DP: Laplace, Gaussian, and exponential. Beyond that, DPpack provides a large toolkit of easily accessible privacy-preserving descriptive statistics functions. These include mean, variance, covariance, and quantiles, as well as histograms and contingency tables.  \nFinally, DPpack provides user-friendly implementation of privacy-preserving versions of logistic regression, SVM, and linear regression, as well as differentially private hyperparameter tuning for each of these models. This extensive collection of implemented differentially private statistics and models permits hassle-free utilization of differential privacy principles in commonly performed statistical analysis.  \nWe plan to continue developing DPpack and make it more comprehensive by including more differentially private machine learning techniques, statistical modeling and inference in the future.  \nKeywords: differential privacy, empirical risk minimization, support vector machines, privacy-preserving, R, randomized mechanism, regression  \n1 Introduction  \nData is an invaluable resource harnessed to inform impactful technology development and guide decision-making. However, utilizing data that contain personally sensitive information (e.g., medical or financial records) poses privacy challenges. Anonymized datasets, as well as statistics and models derived from sensitive datasets are susceptible to attacks that may result in the leakage of private information (Narayanan and Shmatikov, 2008; Ahn, 2015; Sweeney, 2015; Shokri et al., 2017; Zhao et al., 2021) . As technology continues to evolve to become more data-reliant, privacy issues will become increasingly more prevalent, necessitating easy access to tools that provide privacy guarantees when releasing information from sensitive datasets.  \nGiddens and Liu  \nDifferential privacy (DP) (Dwork et al., 2006b) is a popular state-of-the-art framework for providing provable guarantees of privacy for outputs from a statistical or machine learning (ML) procedure. A variety of randomized procedures and mechanisms exist to achieve DP guarantees for a wide range of analyses. These include, to list some examples, summary statistics (Dwork et al., 2006b; Smith, 2011), empirical risk minimization (Chaudhuri et al., 2011; Kifer et al., 2012), classifiers (Chaudhuri and Monteleoni, 2009; Vaidya et al., 2013), deep learning (Abadi et al., 2016; Bu et al. , 2020), Bayesian networks (Zhang et al., 2017a), Bayesian procedures (Dimitrakakiset al., 2014; Wang et al., 2015b), statistical hypothesis testing (Gaboardi et al., 2016; Couch et al., 2019; Barrientos et al., 2019), confidence interval construction (Karwa and Vadhan, 2018; Wang et al., 2019), and synthetic data generation (Zhang et al. , 2017b; Torkzadehmahani et al., 2019; Bowen and Liu, 2020) . Privacy-preserving analysis has also been adopted by many companies in the technology sector, including Google (Guevara et al., 2020), Apple (Apple, 2017), Meta (Nayak, 2020), as well as government agencies like the U.S. Census Bureau (Bureau, 2021) .  \nGiven the popularity of DP, many open-source projects have b","cbCaieEOHG8upDLU","https://ap.wps.com/l/cbCaieEOHG8upDLU","pdf",594885,1,41,"English","en",105,"# Introduction\n## Differential privacy and its motivations\n## Existing DP tools and libraries\n## DPpack and its contributions","[{\"question\":\"What is DPpack, and what problem does it address?\",\"answer\":\"DPpack is an open-source R package that enables differentially private statistical analysis and machine learning. It addresses the need for provable privacy guarantees when working with sensitive data.\"},{\"question\":\"Which differential privacy mechanisms does DPpack currently implement?\",\"answer\":\"DPpack implements three popular DP mechanisms: Laplace, Gaussian, and exponential.\"},{\"question\":\"What kinds of DP functionality does DPpack provide beyond core mechanisms?\",\"answer\":\"DPpack provides privacy-preserving descriptive statistics (e.g., mean, variance, covariance, quantiles, histograms, contingency tables) and privacy-preserving model implementations for logistic regression, SVM, and linear regression, including differentially private hyperparameter tuning.\"}]","DPpack: An R Package for Differentially Private Statistical Analysis and Machine Learning | PDF",1785812504,103,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"dppack-an-r-package-for-differentially-private-statistical-analysis-and-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/dppack-an-r-package-for-differentially-private-statistical-analysis-and-machine-learning/122717/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is DPpack, and what problem does it address?","Question",{"text":75,"@type":76},"DPpack is an open-source R package that enables differentially private statistical analysis and machine learning. It addresses the need for provable privacy guarantees when working with sensitive data.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which differential privacy mechanisms does DPpack currently implement?",{"text":80,"@type":76},"DPpack implements three popular DP mechanisms: Laplace, Gaussian, and exponential.",{"name":82,"@type":73,"acceptedAnswer":83},"What kinds of DP functionality does DPpack provide beyond core mechanisms?",{"text":84,"@type":76},"DPpack provides privacy-preserving descriptive statistics (e.g., mean, variance, covariance, quantiles, histograms, contingency tables) and privacy-preserving model implementations for logistic regression, SVM, and linear regression, including differentially private hyperparameter tuning.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]