Online Binary Models are Promising for Distinguishing Temporally Consistent Computer Usage Profiles
This paper investigates whether computer usage profiles comprised of process-, network-, mouse-, and keystroke-related events are unique and consistent over time in a naturalistic setting, discussing challenges and opportunities of using such profiles in applications of continuous authentication. We...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on biometrics, behavior, and identity science behavior, and identity science, 2022-07, Vol.4 (3), p.412-423 |
|---|---|
| Hauptverfasser: | , , , , , , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 423 |
|---|---|
| container_issue | 3 |
| container_start_page | 412 |
| container_title | IEEE transactions on biometrics, behavior, and identity science |
| container_volume | 4 |
| creator | Giovanini, Luiz Ceschin, Fabricio Silva, Mirela Chen, Aokun Kulkarni, Ramchandra Banda, Sanjay Lysaght, Madison Qiao, Heng Sapountzis, Nikolaos Sun, Ruimin Matthews, Brandon Wu, Dapeng Oliver Gregio, Andre Oliveira, Daniela |
| description | This paper investigates whether computer usage profiles comprised of process-, network-, mouse-, and keystroke-related events are unique and consistent over time in a naturalistic setting, discussing challenges and opportunities of using such profiles in applications of continuous authentication. We collected ecologically-valid computer usage profiles from 31 MS Windows 10 computer users over 8 weeks and submitted this data to comprehensive machine learning analysis involving a diverse set of online and offline classifiers. We found that: (i) profiles were mostly consistent over the 8-week data collection period, with most (83.9%) repeating computer usage habits on a daily basis; (ii) computer usage profiling has the potential to uniquely characterize computer users (with a maximum F-score of 99.90%); (iii) network-related events were the most relevant features to accurately recognize profiles (95.69% of the top features distinguishing users were network-related); and (iv) binary models were the most well-suited for profile recognition, with better results achieved in the online setting compared to the offline setting (maximum F-score of 99.90% vs. 95.50%). |
| doi_str_mv | 10.1109/TBIOM.2022.3179206 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_proquest_journals_2691875787</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9786768</ieee_id><sourcerecordid>2691875787</sourcerecordid><originalsourceid>FETCH-LOGICAL-c295t-d96a09b0f020685205fb17651968d1493d4797af90c36c792c76a9eba32a10283</originalsourceid><addsrcrecordid>eNpNUMtqwzAQFKWFhjQ_0F4EPTtdybYexyZ9BRLSQ3IWii2nCrblSvahf1_lQSks7LC7M7s7CN0TmBIC8mkzW6xXUwqUTlPCJQV2hUaUpTxhGfDrf_gWTUI4AACFTMYYoWLd1rY1eGZb7X_wypWmDlh7gz-9a2yw7R5XzuMXG_qIBxu-jqWNaTrndV3_4LlrQ2yato-w6YbeeLwNen9SqGxtwh26qXQdzOSSx2j79rqZfyTL9fti_rxMCirzPikl0yB3UMXrmMgp5NWOcJYTyURJMpmWGZdcVxKKlBXxz4IzLc1Op1QToCIdo8ezbufd92BCrw5u8G1cqSiTRPCcCx6n6Hmq8C4EbyrVedvE5xUBdfRTnfxURz_Vxc9IejiTrDHmjyC5YJyJ9BdsXXFL</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2691875787</pqid></control><display><type>article</type><title>Online Binary Models are Promising for Distinguishing Temporally Consistent Computer Usage Profiles</title><source>IEEE Electronic Library (IEL)</source><creator>Giovanini, Luiz ; Ceschin, Fabricio ; Silva, Mirela ; Chen, Aokun ; Kulkarni, Ramchandra ; Banda, Sanjay ; Lysaght, Madison ; Qiao, Heng ; Sapountzis, Nikolaos ; Sun, Ruimin ; Matthews, Brandon ; Wu, Dapeng Oliver ; Gregio, Andre ; Oliveira, Daniela</creator><creatorcontrib>Giovanini, Luiz ; Ceschin, Fabricio ; Silva, Mirela ; Chen, Aokun ; Kulkarni, Ramchandra ; Banda, Sanjay ; Lysaght, Madison ; Qiao, Heng ; Sapountzis, Nikolaos ; Sun, Ruimin ; Matthews, Brandon ; Wu, Dapeng Oliver ; Gregio, Andre ; Oliveira, Daniela</creatorcontrib><description>This paper investigates whether computer usage profiles comprised of process-, network-, mouse-, and keystroke-related events are unique and consistent over time in a naturalistic setting, discussing challenges and opportunities of using such profiles in applications of continuous authentication. We collected ecologically-valid computer usage profiles from 31 MS Windows 10 computer users over 8 weeks and submitted this data to comprehensive machine learning analysis involving a diverse set of online and offline classifiers. We found that: (i) profiles were mostly consistent over the 8-week data collection period, with most (83.9%) repeating computer usage habits on a daily basis; (ii) computer usage profiling has the potential to uniquely characterize computer users (with a maximum F-score of 99.90%); (iii) network-related events were the most relevant features to accurately recognize profiles (95.69% of the top features distinguishing users were network-related); and (iv) binary models were the most well-suited for profile recognition, with better results achieved in the online setting compared to the offline setting (maximum F-score of 99.90% vs. 95.50%).</description><identifier>ISSN: 2637-6407</identifier><identifier>EISSN: 2637-6407</identifier><identifier>DOI: 10.1109/TBIOM.2022.3179206</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Analytical models ; Behavioral sciences ; Biological system modeling ; Biometrics (access control) ; Computational modeling ; Computer security ; Computer user profiling ; continuous authentication ; Data collection ; Feature recognition ; Jointly owned property ; Machine learning ; Operating systems ; time series analysis ; user study ; Windows (computer programs)</subject><ispartof>IEEE transactions on biometrics, behavior, and identity science, 2022-07, Vol.4 (3), p.412-423</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c295t-d96a09b0f020685205fb17651968d1493d4797af90c36c792c76a9eba32a10283</citedby><cites>FETCH-LOGICAL-c295t-d96a09b0f020685205fb17651968d1493d4797af90c36c792c76a9eba32a10283</cites><orcidid>0000-0003-3488-0053 ; 0000-0003-1766-5757 ; 0000-0001-6853-8083 ; 0000-0002-2617-0847 ; 0000-0003-2940-5549</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9786768$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,776,780,792,27901,27902,54733</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9786768$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Giovanini, Luiz</creatorcontrib><creatorcontrib>Ceschin, Fabricio</creatorcontrib><creatorcontrib>Silva, Mirela</creatorcontrib><creatorcontrib>Chen, Aokun</creatorcontrib><creatorcontrib>Kulkarni, Ramchandra</creatorcontrib><creatorcontrib>Banda, Sanjay</creatorcontrib><creatorcontrib>Lysaght, Madison</creatorcontrib><creatorcontrib>Qiao, Heng</creatorcontrib><creatorcontrib>Sapountzis, Nikolaos</creatorcontrib><creatorcontrib>Sun, Ruimin</creatorcontrib><creatorcontrib>Matthews, Brandon</creatorcontrib><creatorcontrib>Wu, Dapeng Oliver</creatorcontrib><creatorcontrib>Gregio, Andre</creatorcontrib><creatorcontrib>Oliveira, Daniela</creatorcontrib><title>Online Binary Models are Promising for Distinguishing Temporally Consistent Computer Usage Profiles</title><title>IEEE transactions on biometrics, behavior, and identity science</title><addtitle>TBIOM</addtitle><description>This paper investigates whether computer usage profiles comprised of process-, network-, mouse-, and keystroke-related events are unique and consistent over time in a naturalistic setting, discussing challenges and opportunities of using such profiles in applications of continuous authentication. We collected ecologically-valid computer usage profiles from 31 MS Windows 10 computer users over 8 weeks and submitted this data to comprehensive machine learning analysis involving a diverse set of online and offline classifiers. We found that: (i) profiles were mostly consistent over the 8-week data collection period, with most (83.9%) repeating computer usage habits on a daily basis; (ii) computer usage profiling has the potential to uniquely characterize computer users (with a maximum F-score of 99.90%); (iii) network-related events were the most relevant features to accurately recognize profiles (95.69% of the top features distinguishing users were network-related); and (iv) binary models were the most well-suited for profile recognition, with better results achieved in the online setting compared to the offline setting (maximum F-score of 99.90% vs. 95.50%).</description><subject>Analytical models</subject><subject>Behavioral sciences</subject><subject>Biological system modeling</subject><subject>Biometrics (access control)</subject><subject>Computational modeling</subject><subject>Computer security</subject><subject>Computer user profiling</subject><subject>continuous authentication</subject><subject>Data collection</subject><subject>Feature recognition</subject><subject>Jointly owned property</subject><subject>Machine learning</subject><subject>Operating systems</subject><subject>time series analysis</subject><subject>user study</subject><subject>Windows (computer programs)</subject><issn>2637-6407</issn><issn>2637-6407</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpNUMtqwzAQFKWFhjQ_0F4EPTtdybYexyZ9BRLSQ3IWii2nCrblSvahf1_lQSks7LC7M7s7CN0TmBIC8mkzW6xXUwqUTlPCJQV2hUaUpTxhGfDrf_gWTUI4AACFTMYYoWLd1rY1eGZb7X_wypWmDlh7gz-9a2yw7R5XzuMXG_qIBxu-jqWNaTrndV3_4LlrQ2yato-w6YbeeLwNen9SqGxtwh26qXQdzOSSx2j79rqZfyTL9fti_rxMCirzPikl0yB3UMXrmMgp5NWOcJYTyURJMpmWGZdcVxKKlBXxz4IzLc1Op1QToCIdo8ezbufd92BCrw5u8G1cqSiTRPCcCx6n6Hmq8C4EbyrVedvE5xUBdfRTnfxURz_Vxc9IejiTrDHmjyC5YJyJ9BdsXXFL</recordid><startdate>20220701</startdate><enddate>20220701</enddate><creator>Giovanini, Luiz</creator><creator>Ceschin, Fabricio</creator><creator>Silva, Mirela</creator><creator>Chen, Aokun</creator><creator>Kulkarni, Ramchandra</creator><creator>Banda, Sanjay</creator><creator>Lysaght, Madison</creator><creator>Qiao, Heng</creator><creator>Sapountzis, Nikolaos</creator><creator>Sun, Ruimin</creator><creator>Matthews, Brandon</creator><creator>Wu, Dapeng Oliver</creator><creator>Gregio, Andre</creator><creator>Oliveira, Daniela</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>8FD</scope><scope>L7M</scope><orcidid>https://orcid.org/0000-0003-3488-0053</orcidid><orcidid>https://orcid.org/0000-0003-1766-5757</orcidid><orcidid>https://orcid.org/0000-0001-6853-8083</orcidid><orcidid>https://orcid.org/0000-0002-2617-0847</orcidid><orcidid>https://orcid.org/0000-0003-2940-5549</orcidid></search><sort><creationdate>20220701</creationdate><title>Online Binary Models are Promising for Distinguishing Temporally Consistent Computer Usage Profiles</title><author>Giovanini, Luiz ; Ceschin, Fabricio ; Silva, Mirela ; Chen, Aokun ; Kulkarni, Ramchandra ; Banda, Sanjay ; Lysaght, Madison ; Qiao, Heng ; Sapountzis, Nikolaos ; Sun, Ruimin ; Matthews, Brandon ; Wu, Dapeng Oliver ; Gregio, Andre ; Oliveira, Daniela</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c295t-d96a09b0f020685205fb17651968d1493d4797af90c36c792c76a9eba32a10283</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Analytical models</topic><topic>Behavioral sciences</topic><topic>Biological system modeling</topic><topic>Biometrics (access control)</topic><topic>Computational modeling</topic><topic>Computer security</topic><topic>Computer user profiling</topic><topic>continuous authentication</topic><topic>Data collection</topic><topic>Feature recognition</topic><topic>Jointly owned property</topic><topic>Machine learning</topic><topic>Operating systems</topic><topic>time series analysis</topic><topic>user study</topic><topic>Windows (computer programs)</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Giovanini, Luiz</creatorcontrib><creatorcontrib>Ceschin, Fabricio</creatorcontrib><creatorcontrib>Silva, Mirela</creatorcontrib><creatorcontrib>Chen, Aokun</creatorcontrib><creatorcontrib>Kulkarni, Ramchandra</creatorcontrib><creatorcontrib>Banda, Sanjay</creatorcontrib><creatorcontrib>Lysaght, Madison</creatorcontrib><creatorcontrib>Qiao, Heng</creatorcontrib><creatorcontrib>Sapountzis, Nikolaos</creatorcontrib><creatorcontrib>Sun, Ruimin</creatorcontrib><creatorcontrib>Matthews, Brandon</creatorcontrib><creatorcontrib>Wu, Dapeng Oliver</creatorcontrib><creatorcontrib>Gregio, Andre</creatorcontrib><creatorcontrib>Oliveira, Daniela</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>IEEE transactions on biometrics, behavior, and identity science</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Giovanini, Luiz</au><au>Ceschin, Fabricio</au><au>Silva, Mirela</au><au>Chen, Aokun</au><au>Kulkarni, Ramchandra</au><au>Banda, Sanjay</au><au>Lysaght, Madison</au><au>Qiao, Heng</au><au>Sapountzis, Nikolaos</au><au>Sun, Ruimin</au><au>Matthews, Brandon</au><au>Wu, Dapeng Oliver</au><au>Gregio, Andre</au><au>Oliveira, Daniela</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Online Binary Models are Promising for Distinguishing Temporally Consistent Computer Usage Profiles</atitle><jtitle>IEEE transactions on biometrics, behavior, and identity science</jtitle><stitle>TBIOM</stitle><date>2022-07-01</date><risdate>2022</risdate><volume>4</volume><issue>3</issue><spage>412</spage><epage>423</epage><pages>412-423</pages><issn>2637-6407</issn><eissn>2637-6407</eissn><abstract>This paper investigates whether computer usage profiles comprised of process-, network-, mouse-, and keystroke-related events are unique and consistent over time in a naturalistic setting, discussing challenges and opportunities of using such profiles in applications of continuous authentication. We collected ecologically-valid computer usage profiles from 31 MS Windows 10 computer users over 8 weeks and submitted this data to comprehensive machine learning analysis involving a diverse set of online and offline classifiers. We found that: (i) profiles were mostly consistent over the 8-week data collection period, with most (83.9%) repeating computer usage habits on a daily basis; (ii) computer usage profiling has the potential to uniquely characterize computer users (with a maximum F-score of 99.90%); (iii) network-related events were the most relevant features to accurately recognize profiles (95.69% of the top features distinguishing users were network-related); and (iv) binary models were the most well-suited for profile recognition, with better results achieved in the online setting compared to the offline setting (maximum F-score of 99.90% vs. 95.50%).</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/TBIOM.2022.3179206</doi><tpages>12</tpages><orcidid>https://orcid.org/0000-0003-3488-0053</orcidid><orcidid>https://orcid.org/0000-0003-1766-5757</orcidid><orcidid>https://orcid.org/0000-0001-6853-8083</orcidid><orcidid>https://orcid.org/0000-0002-2617-0847</orcidid><orcidid>https://orcid.org/0000-0003-2940-5549</orcidid></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 2637-6407 |
| ispartof | IEEE transactions on biometrics, behavior, and identity science, 2022-07, Vol.4 (3), p.412-423 |
| issn | 2637-6407 2637-6407 |
| language | eng |
| recordid | cdi_proquest_journals_2691875787 |
| source | IEEE Electronic Library (IEL) |
| subjects | Analytical models Behavioral sciences Biological system modeling Biometrics (access control) Computational modeling Computer security Computer user profiling continuous authentication Data collection Feature recognition Jointly owned property Machine learning Operating systems time series analysis user study Windows (computer programs) |
| title | Online Binary Models are Promising for Distinguishing Temporally Consistent Computer Usage Profiles |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-15T03%3A07%3A58IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Online%20Binary%20Models%20are%20Promising%20for%20Distinguishing%20Temporally%20Consistent%20Computer%20Usage%20Profiles&rft.jtitle=IEEE%20transactions%20on%20biometrics,%20behavior,%20and%20identity%20science&rft.au=Giovanini,%20Luiz&rft.date=2022-07-01&rft.volume=4&rft.issue=3&rft.spage=412&rft.epage=423&rft.pages=412-423&rft.issn=2637-6407&rft.eissn=2637-6407&rft_id=info:doi/10.1109/TBIOM.2022.3179206&rft_dat=%3Cproquest_RIE%3E2691875787%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2691875787&rft_id=info:pmid/&rft_ieee_id=9786768&rfr_iscdi=true |