[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122807-en":3,"doc-seo-122807-105":30,"detail-sidebar-cat-0-en-105":95},{"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},122807,3848291630094,"Emma Wilson","https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","WHERE YOU GO IS WHO YOU ARE - A STUDY ON MACHINE LEARNING BASED SEMANTIC PRIVACY ATTACKS","The document examines privacy risks arising from machine learning–driven semantic inference from raw location data, within the context of growing digital tracking and data brokerage. It analyzes two attack scenarios—location categorization and user profiling—under realistic data inaccuracies. Experiments using the Foursquare dataset and tracking data show meaningful privacy loss even when spatial locations are obfuscated by up to 200m. With obfuscation beyond 1km, spatial signal adds little value, yet temporal information still enables substantial risk. Public POI context strongly amplifies inference, informing policy and individual protection measures.","arXiv :2310 . 17643v1 [ cs .CY] 26 Oct 2023  \nWHERE YOU GO IS WHO YOU ARE-A STUDY ON MACHINE  \nLEARNING BASED SEMANTIC PRIVACY ATTACKS  \nNina Wiedemann 1 ,∗ , Ourania Kounadi2 , Martin Raubal 1 , Krzysztof Janowicz2  \n∗ Corresponding author: [nwiedemann@ethz.ch](nwiedemann@ethz.ch)  \n1 Institute of Cartography and Geoinformation, ETH Zurich, Zurich, Switzerland  \n2 Department of Geography and Regional Research, University of Vienna, Vienna, Austria  \nKeywords location privacy, place labelling, semantic privacy, human mobility  \nABSTRACT  \nConcerns about data privacy are omnipresent, given the increasing usage of digital applications and their underlying business model that includes selling user data. Location data is particularly sensitive since they allow us to infer activity patterns and interests of users, e.g., by categorizing visited locations based on nearby points of interest (POI) . On top of that, machine learning methods provide new powerful tools to interpret big data. In light of these considerations, we raise the following question: What is the actual risk that realistic, machine learning based privacy attacks can obtain meaningful semantic information from raw location data, subject to inaccuracies in the data? In response, we present a systematic analysis of two attack scenarios, namely location categorization and user profiling. Experiments on the Foursquare dataset and tracking data demonstrate the potential for abuse of high-quality spatial information, leading to a significant privacy loss even with location inaccuracy of up to 200m. With location obfuscation of more than 1 km, spatial information hardly adds any value, but a high privacy risk solely from temporal information remains. The availability of public context data such as POIs plays a key role in inference based on spatial information. Our findings point out the risks of ever-growing databases of tracking data and spatial context data, which policymakers should consider for privacy regulations, and which could guide individuals in their personal location protection measures.  \nIntroduction  \nIn the age of big data, an unprecedented amount of information about individuals is publicly available. Not only the information from social media profiles can be exploited to gain rich insights into the private life of individuals, but also data that is collected by applications on-the-fly. Collecting and selling such data has become a business model of commercial consumer data brokers, who distribute individual data of users, oftentimes without their awareness [14] . A particularly popular source is location data, as the whereabouts of people allow rich insights into their daily activities [36, 5, 20, 58], for example, for the purpose of profiling. Even though awareness for (location) privacy has increased in recent years [2], this is oftentimes not reflected in user behavior, which has been termed the “privacy paradox” [63, 7] . Only gradually, companies are reacting to imposed privacy regulations and the efforts of privacy advocates’ groups [27] . For example, AppleTM is giving back control over data sharing decisions in the iPhoneTM , including location data 1 , and StravaTM offers to restrict track-visibility in their app for recording physical activities.2  \n1[https://support.apple.com/guide/iphone/control-the-location-information-you-share-iph3dd5f9be/](https://support.apple.com/guide/iphone/control-the-location-information-you-share-iph3dd5f9be/)[ ](https://support.apple.com/guide/iphone/control-the-location-information-you-share-iph3dd5f9be/)ios  \n2[https://support.strava.com/hc/en-us/articles/115000173384-Edit-Map-Visibility](https://support.strava.com/hc/en-us/articles/115000173384-Edit-Map-Visibility)  \nA PREPRINT-OCTOBER 27, 2023  \nThe simplest way to protect location data is a form of masking or obfuscation of the exact geographic coordinates [44]; i.e., deliberately reducing the data quality [19] . While hiding the exact location may provide som","cbCaiu7KUK8EegBZ","https://ap.wps.com/l/cbCaiu7KUK8EegBZ","pdf",835141,1,23,"English","en",105,"# Abstract\n## Problem and motivation\n## Semantic privacy attack definition\n## Two attack scenarios\n## Experimental evaluation approach\n## Key findings and implications","[{\"question\":\"Why are location data and semantic privacy especially sensitive?\",\"answer\":\"Location data can reveal activity patterns and interests. Machine learning can further infer meaningful semantics from raw coordinates, enabling semantic privacy attacks beyond simple re-identification.\"},{\"question\":\"What two attack scenarios are analyzed in the study?\",\"answer\":\"The study examines (1) location categorization—assigning visited places to categories—and (2) user profiling—aggregating predicted categories across a user’s visits into a behavioral profile.\"},{\"question\":\"How do spatial obfuscation and temporal information affect attack success?\",\"answer\":\"Spatial obfuscation up to about 200m still allows significant privacy loss. Beyond roughly 1km, spatial information contributes little, but a high privacy risk can remain due to temporal information alone.\"},{\"question\":\"What role do public context data such as POIs play?\",\"answer\":\"Public context data like POIs substantially improve inference from spatial information, making semantic attacks more effective and increasing privacy risk.\"}]","WHERE YOU GO IS WHO YOU ARE - A STUDY ON MACHINE LEARNING BASED SEMANTIC PRIVACY ATTACKS | PDF",1785813005,58,{"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":90,"head_meta":92,"extra_data":94,"updated_unix":28},"where-you-go-is-who-you-are-a-study-on-machine-learning-based-semantic-privacy-attacks","",{"@graph":36,"@context":89},[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/where-you-go-is-who-you-are-a-study-on-machine-learning-based-semantic-privacy-attacks/122807/",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",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"Why are location data and semantic privacy especially sensitive?","Question",{"text":75,"@type":76},"Location data can reveal activity patterns and interests. Machine learning can further infer meaningful semantics from raw coordinates, enabling semantic privacy attacks beyond simple re-identification.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What two attack scenarios are analyzed in the study?",{"text":80,"@type":76},"The study examines (1) location categorization—assigning visited places to categories—and (2) user profiling—aggregating predicted categories across a user’s visits into a behavioral profile.",{"name":82,"@type":73,"acceptedAnswer":83},"How do spatial obfuscation and temporal information affect attack success?",{"text":84,"@type":76},"Spatial obfuscation up to about 200m still allows significant privacy loss. Beyond roughly 1km, spatial information contributes little, but a high privacy risk can remain due to temporal information alone.",{"name":86,"@type":73,"acceptedAnswer":87},"What role do public context data such as POIs play?",{"text":88,"@type":76},"Public context data like POIs substantially improve inference from spatial information, making semantic attacks more effective and increasing privacy risk.","https://schema.org",{"og:url":52,"og:type":91,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":93,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,119,124,127,132,135,139],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},6,"Technology",50,"technology",{"id":120,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":122,"slug":123},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":125,"slug":126},30,"research-report",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":130,"slug":131},9,"Religion & Spirituality",20,"religion-spirituality",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":130,"slug":134},"World Cup","world-cup",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":136,"slug":138},10,"Lifestyle","lifestyle",{"id":140,"doc_module":4,"doc_module_name":46,"category_name":141,"show_sort_weight":110,"slug":142},19,"General","general"]