[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127607-en":3,"doc-seo-127607-105":30,"detail-sidebar-cat-0-en-105":92},{"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":20,"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},127607,549768064778,"Finn","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Privacy Preserving Machine Learning for Behavioral Authentication Systems - Conference paper summary","A behavioral authentication (BA) system verifies identity claims by learning users’ behavioral characteristics from profile data. A neural-network classifier can be trained on user profiles to classify presented verification samples; when the predicted class matches the claimed identity, the claim is accepted, avoiding profile-database maintenance. Since neural models remain vulnerable to privacy attacks, the paper proposes a non-cryptographic approach using random projection to protect training and test data. It applies dense-to-sparse projection to reduce computation and demonstrates strong performance and robustness against privacy and security threats.","Privacy Preserving Machine Learning for Behavioral  \nAuthentication Systems  \nMd Morshedul Islam  \nConcordia University of Edmonton Edmonton, Alberta, Canada [mdmorshedul.islam@concordia.ab.ca](mdmorshedul.islam@concordia.ab.ca)  \nMd Abdur Rafiq  \nConcordia University of Edmonton Edmonton, Alberta[mrafiq@student.concordia.ab.ca](mrafiq@student.concordia.ab.ca)  \nABSTRACT  \nA behavioral authentication (BA) system uses the behavioral characteristics of users to verify their identity claims. A BA verification algorithm can be constructed by training a neural network (NN) classifier on users’ profiles. The trained NN model classifies the presented verification data, and if the classification matches the claimed identity, the verification algorithm accepts the claim. This classification-based approach removes the need to maintain a profile database. However, similar to other NN architectures, the NN classifier of the BA system is vulnerable to privacy attacks. To protect the privacy of training and test data used in an NN different techniques are widely used. In this paper, our focus is on a noncrypto-based approach, and we used random projection (RP) to ensure data privacy in an NN model. RP is a distance-preserving transformation based on a random matrix. Before sharing the profiles with the verifier, users will transform their profiles by RP and keep their matrices secret. To reduce the computation load in RP, we use sparse random projection, which is very effective for lowcompute devices. Along with correctness and security properties, our system can ensure the changeability property of the BA system. We also introduce an ML-based privacy attack, and our proposed system is robust against this and other privacy and security attacks. We implemented our approach on three existing behavioral BA systems and achieved a below 2.0% FRR and a below 1.0% FAR rate. Moreover, the machine learning-based privacy attacker can only recover below 3.0% to 12.0% of features from a portion of the projected profiles. However, these recovered features are not sufficient to know details about the users’ behavioral pattern or to be used in a subsequent attack. Our approach is general and can be used in other NN-based BA systems as well as in traditional biometric systems.  \nKEYWORDS  \nBA system, Privacy attack, Privacy-preserving NN model, Random projection.  \n1 INTRODUCTION  \nOver the last few years, the world has witnessed the beginning of a revolution taking shape in the field of technology.The smartphone is one of the most significant technological advancements. Recent studies have demonstrated the feasibility of extracting behavioral  \nThis work is licensed under the Creative Commons Attribution 4.0 International License. To view a copy of this license visit [https://creativecommons.org/licenses/by/4.0/ or](https://creativecommons.org/licenses/by/4.0/ or) send a  \nletter to Creative Commons, PO Box 1866, Mountain View, CA 94042, USA. YYYY(X), 1ś13  \n© YYYY Copyright held by the owner/author(s) . [https://doi.org/XXXXXXX.XXXXXXX](https://doi.org/XXXXXXX.XXXXXXX)  \ndata, such as touch dynamics, keystroke dynamics, and gait recognition, utilizing smartphone sensors and peripherals. A Behavioral Authentication (BA) system [15, 19, 29, 33] utilizes this captured behavioral data for users’ authentication. When users use their smart devices, the BA system collects behavioral data from the devices, creates profiles, and sends them to a verifier. The verifier will either store the profiles or use them for verification decisions. Typically, a verifier is an online server that renders real-time verification decisions for a verification claim. In a multi-factor authentication system, BA systems have been used to strengthen other factors. Additionally, BA systems offer a number of alluring features, including continuous authentication [23] and security against łcredentialsharingž without the requirement for additional hardwares.  \nA profile in a BA system con","cbCaia9LA6NBSjH6","https://ap.wps.com/l/cbCaia9LA6NBSjH6","pdf",736014,1,13,"English","en",105,"# Abstract\n# Introduction\n## Behavioral authentication overview\n## Neural-network-based verification\n# Privacy-preserving approach\n## Random projection and sparse random projection\n## Threat model and robustness\n# Experimental results\n## FRR and FAR performance\n## Feature recovery by ML-based attacker","[{\"question\":\"How does a behavioral authentication (BA) system verify identity claims?\",\"answer\":\"It uses behavioral characteristics to train a verification algorithm, often a neural-network classifier. The system classifies presented verification data and accepts the claim when the classification matches the claimed identity.\"},{\"question\":\"Why is privacy protection necessary for neural-network-based BA systems?\",\"answer\":\"Because the neural-network classifier is vulnerable to privacy attacks that can exploit training or test data. The paper addresses this by transforming profiles before sharing them with the verifier.\"},{\"question\":\"What privacy-preserving method does the paper propose?\",\"answer\":\"It uses non-cryptographic random projection, where users transform their profiles with a random matrix and keep the matrices secret. Sparse random projection is used to reduce computation for low-compute devices.\"}]","Privacy Preserving Machine Learning for Behavioral Authentication Systems - Conference paper summary | PDF",1785940252,33,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"privacy-preserving-machine-learning-for-behavioral-authentication-systems-conference-paper-summary","",{"@graph":36,"@context":86},[37,54,69],{"@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/privacy-preserving-machine-learning-for-behavioral-authentication-systems-conference-paper-summary/127607/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"How does a behavioral authentication (BA) system verify identity claims?","Question",{"text":76,"@type":77},"It uses behavioral characteristics to train a verification algorithm, often a neural-network classifier. The system classifies presented verification data and accepts the claim when the classification matches the claimed identity.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Why is privacy protection necessary for neural-network-based BA systems?",{"text":81,"@type":77},"Because the neural-network classifier is vulnerable to privacy attacks that can exploit training or test data. The paper addresses this by transforming profiles before sharing them with the verifier.",{"name":83,"@type":74,"acceptedAnswer":84},"What privacy-preserving method does the paper propose?",{"text":85,"@type":77},"It uses non-cryptographic random projection, where users transform their profiles with a random matrix and keep the matrices secret. Sparse random projection is used to reduce computation for low-compute devices.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]