Multi-modal decision fusion for continuous authentication

Lex Fridman, Ariel Stolerman, Sayandeep Acharya, Patrick Brennan, Patrick Juola, Rachel Greenstadt, Moshe Kam, Felix Gomez

    Research output: Contribution to journalArticle

    Abstract

    Active authentication is the process of continuously verifying a user based on their ongoing interaction with a computer. In this study, we consider a representative collection of behavioral biometrics: two low-level modalities of keystroke dynamics and mouse movement, and a high-level modality of stylometry. We develop a sensor for each modality and organize the sensors as a parallel binary decision fusion architecture. We consider several applications for this authentication system, with a particular focus on secure distributed communication. We test our approach on a dataset collected from 67 users, each working individually in an office environment for a period of approximately one week. We are able to characterize the performance of the system with respect to intruder detection time and robustness to adversarial attacks, and to quantify the contribution of each modality to the overall performance.

    Original languageEnglish (US)
    Pages (from-to)142-156
    Number of pages15
    JournalComputers and Electrical Engineering
    Volume41
    Issue numberC
    DOIs
    StatePublished - Jan 1 2015

    Fingerprint

    Authentication
    Fusion reactions
    Sensors
    Biometrics
    Communication

    Keywords

    • Active authentication
    • Behavioral biometrics
    • Decision fusion
    • Distributed communication
    • Multimodal biometric systems
    • Security and privacy

    ASJC Scopus subject areas

    • Control and Systems Engineering
    • Computer Science(all)
    • Electrical and Electronic Engineering

    Cite this

    Fridman, L., Stolerman, A., Acharya, S., Brennan, P., Juola, P., Greenstadt, R., ... Gomez, F. (2015). Multi-modal decision fusion for continuous authentication. Computers and Electrical Engineering, 41(C), 142-156. https://doi.org/10.1016/j.compeleceng.2014.10.018

    Multi-modal decision fusion for continuous authentication. / Fridman, Lex; Stolerman, Ariel; Acharya, Sayandeep; Brennan, Patrick; Juola, Patrick; Greenstadt, Rachel; Kam, Moshe; Gomez, Felix.

    In: Computers and Electrical Engineering, Vol. 41, No. C, 01.01.2015, p. 142-156.

    Research output: Contribution to journalArticle

    Fridman, L, Stolerman, A, Acharya, S, Brennan, P, Juola, P, Greenstadt, R, Kam, M & Gomez, F 2015, 'Multi-modal decision fusion for continuous authentication', Computers and Electrical Engineering, vol. 41, no. C, pp. 142-156. https://doi.org/10.1016/j.compeleceng.2014.10.018
    Fridman L, Stolerman A, Acharya S, Brennan P, Juola P, Greenstadt R et al. Multi-modal decision fusion for continuous authentication. Computers and Electrical Engineering. 2015 Jan 1;41(C):142-156. https://doi.org/10.1016/j.compeleceng.2014.10.018
    Fridman, Lex ; Stolerman, Ariel ; Acharya, Sayandeep ; Brennan, Patrick ; Juola, Patrick ; Greenstadt, Rachel ; Kam, Moshe ; Gomez, Felix. / Multi-modal decision fusion for continuous authentication. In: Computers and Electrical Engineering. 2015 ; Vol. 41, No. C. pp. 142-156.
    @article{946dff5e70c54ff799a700b7e7124c98,
    title = "Multi-modal decision fusion for continuous authentication",
    abstract = "Active authentication is the process of continuously verifying a user based on their ongoing interaction with a computer. In this study, we consider a representative collection of behavioral biometrics: two low-level modalities of keystroke dynamics and mouse movement, and a high-level modality of stylometry. We develop a sensor for each modality and organize the sensors as a parallel binary decision fusion architecture. We consider several applications for this authentication system, with a particular focus on secure distributed communication. We test our approach on a dataset collected from 67 users, each working individually in an office environment for a period of approximately one week. We are able to characterize the performance of the system with respect to intruder detection time and robustness to adversarial attacks, and to quantify the contribution of each modality to the overall performance.",
    keywords = "Active authentication, Behavioral biometrics, Decision fusion, Distributed communication, Multimodal biometric systems, Security and privacy",
    author = "Lex Fridman and Ariel Stolerman and Sayandeep Acharya and Patrick Brennan and Patrick Juola and Rachel Greenstadt and Moshe Kam and Felix Gomez",
    year = "2015",
    month = "1",
    day = "1",
    doi = "10.1016/j.compeleceng.2014.10.018",
    language = "English (US)",
    volume = "41",
    pages = "142--156",
    journal = "Computers and Electrical Engineering",
    issn = "0045-7906",
    publisher = "Elsevier Limited",
    number = "C",

    }

    TY - JOUR

    T1 - Multi-modal decision fusion for continuous authentication

    AU - Fridman, Lex

    AU - Stolerman, Ariel

    AU - Acharya, Sayandeep

    AU - Brennan, Patrick

    AU - Juola, Patrick

    AU - Greenstadt, Rachel

    AU - Kam, Moshe

    AU - Gomez, Felix

    PY - 2015/1/1

    Y1 - 2015/1/1

    N2 - Active authentication is the process of continuously verifying a user based on their ongoing interaction with a computer. In this study, we consider a representative collection of behavioral biometrics: two low-level modalities of keystroke dynamics and mouse movement, and a high-level modality of stylometry. We develop a sensor for each modality and organize the sensors as a parallel binary decision fusion architecture. We consider several applications for this authentication system, with a particular focus on secure distributed communication. We test our approach on a dataset collected from 67 users, each working individually in an office environment for a period of approximately one week. We are able to characterize the performance of the system with respect to intruder detection time and robustness to adversarial attacks, and to quantify the contribution of each modality to the overall performance.

    AB - Active authentication is the process of continuously verifying a user based on their ongoing interaction with a computer. In this study, we consider a representative collection of behavioral biometrics: two low-level modalities of keystroke dynamics and mouse movement, and a high-level modality of stylometry. We develop a sensor for each modality and organize the sensors as a parallel binary decision fusion architecture. We consider several applications for this authentication system, with a particular focus on secure distributed communication. We test our approach on a dataset collected from 67 users, each working individually in an office environment for a period of approximately one week. We are able to characterize the performance of the system with respect to intruder detection time and robustness to adversarial attacks, and to quantify the contribution of each modality to the overall performance.

    KW - Active authentication

    KW - Behavioral biometrics

    KW - Decision fusion

    KW - Distributed communication

    KW - Multimodal biometric systems

    KW - Security and privacy

    UR - http://www.scopus.com/inward/record.url?scp=84927731323&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84927731323&partnerID=8YFLogxK

    U2 - 10.1016/j.compeleceng.2014.10.018

    DO - 10.1016/j.compeleceng.2014.10.018

    M3 - Article

    AN - SCOPUS:84927731323

    VL - 41

    SP - 142

    EP - 156

    JO - Computers and Electrical Engineering

    JF - Computers and Electrical Engineering

    SN - 0045-7906

    IS - C

    ER -