Activelinguisticauthentication using real-time stylometric evaluation for multi-modal decision fusion

Ariel Stolerman, Alex Fridman, Rachel Greenstadt, Patrick Brennan, Patrick Juola

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    Active authentication is the process of continuously verifying a user based on his/her ongoing interactions with a computer. Forensic sty-lometry is the study of linguistic style applied to author (user) identification. This paper evaluates the Active Linguistic Authentication Dataset, collected from users working individually in an office environment over a period of one week. It considers a battery of stylometric modalities as a representative collection of high-level behavioral biometrics. While a previous study conducted a partial evaluation of the dataset with data from fourteen users, this paper considers the complete dataset comprising data from 67 users. Another significant difference is in the type of evaluation: instead of using day-based or data-based (number-of-characters) windows for classification, the evaluation employs time-based, overlapping sliding windows. This tests the ability to produce authentication decisions every 10 to 60 seconds, which is highly applicable to real-world active security systems. Sensor evaluation is conducted via cross-validation, measuring the false acceptance and false rejection rates (FAR/FRR). The results demonstrate that, under realistic settings, stylometric sensors perform with considerable effectiveness down to 0/0.5 FAR/FRR for decisions produced every 60 seconds and available 95% of the time.

    Original languageEnglish (US)
    Title of host publicationAdvances in Digital Forensics X - 10th IFIP WG 11.9 International Conference, Revised Selected Papers
    EditorsGilbert Peterson, Sujeet Shenoi
    PublisherSpringer New York LLC
    Pages165-183
    Number of pages19
    ISBN (Electronic)9783662449516
    StatePublished - Jan 1 2014
    Event10th IFIP WG 11.9 International Conference on Digital Forensics - Vienna, Austria
    Duration: Jan 8 2014Jan 10 2014

    Publication series

    NameIFIP Advances in Information and Communication Technology
    Volume433
    ISSN (Print)1868-4238

    Conference

    Conference10th IFIP WG 11.9 International Conference on Digital Forensics
    CountryAustria
    CityVienna
    Period1/8/141/10/14

    Fingerprint

    Authentication
    Fusion reactions
    Linguistics
    Sensors
    Biometrics
    Security systems
    Evaluation
    Fusion
    Sensor

    Keywords

    • Active authentication
    • Authorship verification
    • Stylometry

    ASJC Scopus subject areas

    • Information Systems
    • Computer Networks and Communications
    • Information Systems and Management

    Cite this

    Stolerman, A., Fridman, A., Greenstadt, R., Brennan, P., & Juola, P. (2014). Activelinguisticauthentication using real-time stylometric evaluation for multi-modal decision fusion. In G. Peterson, & S. Shenoi (Eds.), Advances in Digital Forensics X - 10th IFIP WG 11.9 International Conference, Revised Selected Papers (pp. 165-183). (IFIP Advances in Information and Communication Technology; Vol. 433). Springer New York LLC.

    Activelinguisticauthentication using real-time stylometric evaluation for multi-modal decision fusion. / Stolerman, Ariel; Fridman, Alex; Greenstadt, Rachel; Brennan, Patrick; Juola, Patrick.

    Advances in Digital Forensics X - 10th IFIP WG 11.9 International Conference, Revised Selected Papers. ed. / Gilbert Peterson; Sujeet Shenoi. Springer New York LLC, 2014. p. 165-183 (IFIP Advances in Information and Communication Technology; Vol. 433).

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Stolerman, A, Fridman, A, Greenstadt, R, Brennan, P & Juola, P 2014, Activelinguisticauthentication using real-time stylometric evaluation for multi-modal decision fusion. in G Peterson & S Shenoi (eds), Advances in Digital Forensics X - 10th IFIP WG 11.9 International Conference, Revised Selected Papers. IFIP Advances in Information and Communication Technology, vol. 433, Springer New York LLC, pp. 165-183, 10th IFIP WG 11.9 International Conference on Digital Forensics, Vienna, Austria, 1/8/14.
    Stolerman A, Fridman A, Greenstadt R, Brennan P, Juola P. Activelinguisticauthentication using real-time stylometric evaluation for multi-modal decision fusion. In Peterson G, Shenoi S, editors, Advances in Digital Forensics X - 10th IFIP WG 11.9 International Conference, Revised Selected Papers. Springer New York LLC. 2014. p. 165-183. (IFIP Advances in Information and Communication Technology).
    Stolerman, Ariel ; Fridman, Alex ; Greenstadt, Rachel ; Brennan, Patrick ; Juola, Patrick. / Activelinguisticauthentication using real-time stylometric evaluation for multi-modal decision fusion. Advances in Digital Forensics X - 10th IFIP WG 11.9 International Conference, Revised Selected Papers. editor / Gilbert Peterson ; Sujeet Shenoi. Springer New York LLC, 2014. pp. 165-183 (IFIP Advances in Information and Communication Technology).
    @inproceedings{66c950ea53c54252b6d65b40b51b7390,
    title = "Activelinguisticauthentication using real-time stylometric evaluation for multi-modal decision fusion",
    abstract = "Active authentication is the process of continuously verifying a user based on his/her ongoing interactions with a computer. Forensic sty-lometry is the study of linguistic style applied to author (user) identification. This paper evaluates the Active Linguistic Authentication Dataset, collected from users working individually in an office environment over a period of one week. It considers a battery of stylometric modalities as a representative collection of high-level behavioral biometrics. While a previous study conducted a partial evaluation of the dataset with data from fourteen users, this paper considers the complete dataset comprising data from 67 users. Another significant difference is in the type of evaluation: instead of using day-based or data-based (number-of-characters) windows for classification, the evaluation employs time-based, overlapping sliding windows. This tests the ability to produce authentication decisions every 10 to 60 seconds, which is highly applicable to real-world active security systems. Sensor evaluation is conducted via cross-validation, measuring the false acceptance and false rejection rates (FAR/FRR). The results demonstrate that, under realistic settings, stylometric sensors perform with considerable effectiveness down to 0/0.5 FAR/FRR for decisions produced every 60 seconds and available 95{\%} of the time.",
    keywords = "Active authentication, Authorship verification, Stylometry",
    author = "Ariel Stolerman and Alex Fridman and Rachel Greenstadt and Patrick Brennan and Patrick Juola",
    year = "2014",
    month = "1",
    day = "1",
    language = "English (US)",
    series = "IFIP Advances in Information and Communication Technology",
    publisher = "Springer New York LLC",
    pages = "165--183",
    editor = "Gilbert Peterson and Sujeet Shenoi",
    booktitle = "Advances in Digital Forensics X - 10th IFIP WG 11.9 International Conference, Revised Selected Papers",
    address = "United States",

    }

    TY - GEN

    T1 - Activelinguisticauthentication using real-time stylometric evaluation for multi-modal decision fusion

    AU - Stolerman, Ariel

    AU - Fridman, Alex

    AU - Greenstadt, Rachel

    AU - Brennan, Patrick

    AU - Juola, Patrick

    PY - 2014/1/1

    Y1 - 2014/1/1

    N2 - Active authentication is the process of continuously verifying a user based on his/her ongoing interactions with a computer. Forensic sty-lometry is the study of linguistic style applied to author (user) identification. This paper evaluates the Active Linguistic Authentication Dataset, collected from users working individually in an office environment over a period of one week. It considers a battery of stylometric modalities as a representative collection of high-level behavioral biometrics. While a previous study conducted a partial evaluation of the dataset with data from fourteen users, this paper considers the complete dataset comprising data from 67 users. Another significant difference is in the type of evaluation: instead of using day-based or data-based (number-of-characters) windows for classification, the evaluation employs time-based, overlapping sliding windows. This tests the ability to produce authentication decisions every 10 to 60 seconds, which is highly applicable to real-world active security systems. Sensor evaluation is conducted via cross-validation, measuring the false acceptance and false rejection rates (FAR/FRR). The results demonstrate that, under realistic settings, stylometric sensors perform with considerable effectiveness down to 0/0.5 FAR/FRR for decisions produced every 60 seconds and available 95% of the time.

    AB - Active authentication is the process of continuously verifying a user based on his/her ongoing interactions with a computer. Forensic sty-lometry is the study of linguistic style applied to author (user) identification. This paper evaluates the Active Linguistic Authentication Dataset, collected from users working individually in an office environment over a period of one week. It considers a battery of stylometric modalities as a representative collection of high-level behavioral biometrics. While a previous study conducted a partial evaluation of the dataset with data from fourteen users, this paper considers the complete dataset comprising data from 67 users. Another significant difference is in the type of evaluation: instead of using day-based or data-based (number-of-characters) windows for classification, the evaluation employs time-based, overlapping sliding windows. This tests the ability to produce authentication decisions every 10 to 60 seconds, which is highly applicable to real-world active security systems. Sensor evaluation is conducted via cross-validation, measuring the false acceptance and false rejection rates (FAR/FRR). The results demonstrate that, under realistic settings, stylometric sensors perform with considerable effectiveness down to 0/0.5 FAR/FRR for decisions produced every 60 seconds and available 95% of the time.

    KW - Active authentication

    KW - Authorship verification

    KW - Stylometry

    UR - http://www.scopus.com/inward/record.url?scp=84911062702&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84911062702&partnerID=8YFLogxK

    M3 - Conference contribution

    AN - SCOPUS:84911062702

    T3 - IFIP Advances in Information and Communication Technology

    SP - 165

    EP - 183

    BT - Advances in Digital Forensics X - 10th IFIP WG 11.9 International Conference, Revised Selected Papers

    A2 - Peterson, Gilbert

    A2 - Shenoi, Sujeet

    PB - Springer New York LLC

    ER -