[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117009-en":3,"doc-seo-117009-105":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},117009,16904993612988,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Consideration of Data Security and Privacy Using Machine Learning Techniques","As machine learning expands across domains, it increasingly relies on big data gathered via crowdsourcing and obtained online, which often contains sensitive private attributes such as identification numbers, mobile contacts, and medical records. The core challenge is protecting this data effectively and cheaply while enabling learning. The work analyzes privacy dilemmas and potential exploitation, then reviews privacy-protection features and techniques in machine-learning algorithms. A CNN-based network combined with a secure privacy approach is proposed to enhance classification accuracy by using layer-wise privacy budgets under Gaussian noise and stochastic gradient descent, with experiments reporting an accuracy around 99.05% while balancing privacy protection.","Consideration of Data Security and Privacy Using Machine  \nLearning Techniques  \nThanh Chi Phan1, Hung Chi Tran2  \n1Quang Tri Teacher Training College, Hanoi University of Science and Technology, Vietnam  \n2Information Technology Engineer, IT Center, Quang Tri Teacher Training College, Dong Ha City, Quang Tri Province, Vietnam  \nArticle Info ABSTRACT  \nArticle history:  \nReceived November 07, 2023 Revised December 01, 2023 Accepted December 05, 2023  \nKeywords:  \nMachine learning Security Cryptography  \nPrivacy-preserving data protocol  \nCorresponding Author:  \nThanh Chi Phan  \nQuang Tri Teacher Training College  \nAs artificial intelligence becomes more and more prevalent, machine learning algorithms are being used in a wider range of domains. Big data and processing power, which are typically gathered via crowdsourcing and acquired online, are essential for the effectiveness of machine learning. Sensitive and private data, such as ID numbers, personal mobile phone numbers, and medical records, are frequently included in the data acquired for machine learning training. A significant issue is how to effectively and cheaply protect sensitive private data. With this type of issue in mind, this article first discusses the privacy dilemma in machine learning and how it might be exploited before summarizing the features and techniques for protecting privacy in machine learning algorithms. Next, the combination of a network of convolutional neural networks and a different secure privacy approach is suggested to improve the accuracy of classification of the various algorithms that employ noise to safeguard privacy. This approach can acquire each layer's privacy budget of a neural network and completely incorporates the properties of Gaussian distribution and difference. Lastly, the Gaussian noise scale is set, and the sensitive information in the data is preserved by using the gradient value of a stochastic gradient descent technique. The experimental results showed that a balance of better accuracy of 99.05% between the accessibility and privacy protection of the training data set could be achieved by modifying the depth differential privacy model's parameters depending on variations in private information in the data.  \nThis is an open access article under the CC BY-SA license.  \nHanoi University of Science and Technology Vietnam  \nEmail: [thanhpc.sp@gmail.com](thanhpc.sp@gmail.com)  \n1. INTRODUCTION  \nCurrently, the primary focus of artificial intelligence is data, and both domestically and internationally, there is a growing interest in protecting personal data. Unauthorized use of private, sensitive information, whether on the internet or offline, is punishable by law. In 2018, the European Union put forth explicit guidelines regarding the management of personal data that businesses gather. Companies are no longer allowed to gather, distribute, or analyze user data without consent. The implementation of protecting privacy in machine learning requires taking into account the peculiarities of machine learning in addition to employing regulations to restrict information leakage [1] . The primary assumption is to guarantee that private and sensitive data won't be either provided or received by unauthorized individuals throughout the training process.  \nFigure 1. A computer vision model is used by an automotive system to recognize network intrusion  \ndetection systems [2] .  \nTraditional neural network training involves data collectors gathering all parties' data, which is subsequently taught by centralized learning, as Figure 1 illustrates. As in the case of mobile application developers, the information collector and the data analyst might work together [2] . Additionally, it might be multiparty, for example, when developers exchange data with different data analytics firms. It is evident that in the centralized learning mode, users find it challenging to maintain possession of the data once it has been gathered, and they are also u","cbCailPGQkrBGDoK","https://ap.wps.com/l/cbCailPGQkrBGDoK","pdf",631202,1,13,"English","en",105,"# Introduction\n## Privacy protection challenges in machine learning\n## Centralized learning and data control limits\n## Federated learning and remaining privacy threats\n## Differential privacy approaches and noise-based protection","[{\"question\":\"Why does data security and privacy matter for machine learning?\",\"answer\":\"Machine learning training often uses data collected online or through crowdsourcing, which may include sensitive personal information. Protecting confidentiality is essential to prevent unauthorized access or leakage during training.\"},{\"question\":\"How do the article’s privacy methods aim to improve classification while protecting privacy?\",\"answer\":\"It proposes combining a convolutional neural network approach with a secure privacy technique that uses noise to safeguard privacy. The method targets improved classification accuracy while accounting for layer-wise privacy budgets under Gaussian noise.\"},{\"question\":\"What role does stochastic gradient descent and Gaussian noise play in preserving sensitive information?\",\"answer\":\"The approach sets a Gaussian noise scale and preserves sensitive information using gradient values obtained from a stochastic gradient descent technique, thereby reducing the ability to recover original training data.\"}]","Consideration of Data Security and Privacy Using Machine Learning Techniques | PDF",1785673064,33,{"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},"consideration-of-data-security-and-privacy-using-machine-learning-techniques","",{"@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/consideration-of-data-security-and-privacy-using-machine-learning-techniques/117009/",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","2026-08-02",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},"Why does data security and privacy matter for machine learning?","Question",{"text":75,"@type":76},"Machine learning training often uses data collected online or through crowdsourcing, which may include sensitive personal information. Protecting confidentiality is essential to prevent unauthorized access or leakage during training.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How do the article’s privacy methods aim to improve classification while protecting privacy?",{"text":80,"@type":76},"It proposes combining a convolutional neural network approach with a secure privacy technique that uses noise to safeguard privacy. The method targets improved classification accuracy while accounting for layer-wise privacy budgets under Gaussian noise.",{"name":82,"@type":73,"acceptedAnswer":83},"What role does stochastic gradient descent and Gaussian noise play in preserving sensitive information?",{"text":84,"@type":76},"The approach sets a Gaussian noise scale and preserves sensitive information using gradient values obtained from a stochastic gradient descent technique, thereby reducing the ability to recover original training data.","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"]