Gesture and Sociability-based Continuous Authentication on Smart Mobile Devices

In this paper, we propose a new continuous verification platform on smart mobile devices. To this end, we integrate gesture-based features with interaction with social networking apps to verify user identities without minimum requirement for a password, pin code or biometric means. The continuous verification subsystem of this work proposes a novel two-step system for verification of users. The subsystem works by having two accurate models working as a primary and backup; when the primary fails the backup takes over to confirm or deny the conclusion of the primary model. The false acceptance rate (FAR) and false rejection rate (FRR) achieved under the proposed two-step system are shown to be 2.54% and 1.98% respectively, compared to the FAR and FRR of single-step verification, which achieved 3.15% and 9.13% respectively. Furthermore, the proposed system also improves the stability of continuous verification. In this work we show that the single step systems are inconsistent when analyzing small feature sets or slightly varied datasets. During both of these instances, the proposed system stays consistent, maintaining a high verification rate.

[1]  John J. Leggett,et al.  Dynamic Identity Verification via Keystroke Characteristics , 1991, Int. J. Man Mach. Stud..

[2]  Luca Foschini,et al.  Quantifying User Reputation Scores, Data Trustworthiness, and User Incentives in Mobile Crowd-Sensing , 2017, IEEE Access.

[3]  Burak Kantarci,et al.  SOBER-MCS: Sociability-Oriented and Battery Efficient Recruitment for Mobile Crowd-Sensing , 2018, Sensors.

[4]  Burak Kantarci,et al.  Mobile behaviometric framework for sociability assessment and identification of smartphone users , 2016, 2016 IEEE Symposium on Computers and Communication (ISCC).

[5]  Yevgeniy Vahlis,et al.  Is it really you?: user identification via adaptive behavior fingerprinting , 2014, CODASPY '14.

[6]  Burak Kantarci,et al.  A mobile platform for sociability-based continuous identification , 2016, 2016 IEEE 21st International Workshop on Computer Aided Modelling and Design of Communication Links and Networks (CAMAD).

[7]  Ahmed Ramadan,et al.  Touch-input based continuous authentication using gesture-level and session-level features , 2017, 2017 8th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON).

[8]  Diana Adler,et al.  Using Multivariate Statistics , 2016 .

[9]  M. Kubát.  An Introduction to Machine Learning , 2017, Springer International Publishing.

[10]  Mike Sharples,et al.  Human-Computer Interaction , 1996, Artificial Intelligence.

[11]  Li Lu,et al.  Safeguard: User Reauthentication on Smartphones via Behavioral Biometrics , 2015, IEEE Transactions on Computational Social Systems.

[12]  Machine learning methods for human-computer interaction [tutorial] , 2012, 2012 IEEE Haptics Symposium (HAPTICS).

[13]  Peter Xiaoping Liu,et al.  Structural Results for Combined Continuous User Authentication and Intrusion Detection in High Security Mobile Ad-Hoc Networks , 2011, IEEE Transactions on Wireless Communications.

[14]  Hai Huang,et al.  You Are How You Touch: User Verification on Smartphones via Tapping Behaviors , 2014, 2014 IEEE 22nd International Conference on Network Protocols.

[15]  Burak Kantarci,et al.  Social Behaviometrics for Personalized Devices in the Internet of Things Era , 2017, IEEE Access.

[16]  Andrea Bondavalli,et al.  Continuous and Transparent User Identity Verification for Secure Internet Services , 2015, IEEE Transactions on Dependable and Secure Computing.

[17]  Zhongmin Cai,et al.  MouseIdentity: Modeling Mouse-Interaction Behavior for a User Verification System , 2016, IEEE Transactions on Human-Machine Systems.

[18]  Duncan S. Wong,et al.  Touch Gestures Based Biometric Authentication Scheme for Touchscreen Mobile Phones , 2012, Inscrypt.

[19]  Stephanie Schuckers,et al.  Effect of data size on performance of free-text keystroke authentication , 2015, IEEE International Conference on Identity, Security and Behavior Analysis (ISBA 2015).

[20]  Burak Kantarci,et al.  Anchor-Assisted and Vote-Based Trustworthiness Assurance in Smart City Crowdsensing , 2016, IEEE Access.

[21]  Burak Kantarci,et al.  COVERS-UP: Collaborative Verification of Smart User Profiles for social sustainability of smart cities , 2017 .

[22]  Burak Kantarci,et al.  The Smart Citizen Factor in Trustworthy Smart City Crowdsensing , 2016, IT Professional.

[23]  Stephanie Schuckers,et al.  Shared research dataset to support development of keystroke authentication , 2014, IEEE International Joint Conference on Biometrics.

[24]  J. Guzmán.  Regression Models for Categorical Dependent Variables Using Stata , 2013 .

[25]  Dzmitry Kliazovich,et al.  Game-Theoretic Recruitment of Sensing Service Providers for Trustworthy Cloud-Centric Internet-of-Things (IoT) Applications , 2016, 2016 IEEE Globecom Workshops (GC Wkshps).