Continuous Authentication of Smartphones Based on Screen-Touch Trajectories

Yuan Jiao

¹The School of Computer and Information Engineering, Chuzhou University, Chuzhou, Anhui 239000, China

*Corresponding author

As smartphones become essential tools for daily activities, security concerns, particularly in mobile payments and personal privacy, are becoming increasingly critical. Traditional lock screens and password-based authentication systems are vulnerable to various threats, such as unauthorized access and identity theft. To address these issues, this paper proposes an advanced continuous authentication method that verifies user identity based on unique screen-touch trajectories. Using machine learning algorithms, the authentication system analyzes real-time screen-touch trajectories from user interactions with the touchscreen, capturing behavioral patterns that are highly specific to individual users. This proposed continuous authentication framework enables the system to authenticate users seamlessly and continuously throughout device usage, ensuring ongoing protection against unauthorized access, financial fraud, and privacy breaches. Experimental results demonstrate that the Random Forest algorithm outperforms other methods in terms of recognition accuracy and response efficiency, offering a reliable and scalable solution. The paper also explores the integration of this authentication approach into existing smartphone security frameworks, showcasing its potential to significantly enhance network security, particularly in high-risk applications such as mobile payments and personal data access.

Continuous authentication, mobile payments and personal privacy, screen-touch trajectories, smartphone security frameworks, payment security

Guozhu Zhao, Yuan Jiao, Jianyu Zhuo, Yu Chen, Chuanzhen Ju, and Yaxin Wang (2024). Continuous Authentication of Smartphones Based on Screen-Touch Trajectories. Journal of Networking and Network Applications, Volume 4, Issue 3, pp. 102–108. https://doi.org/10.33969/J-NaNA.2024.040301.

[1] Saeed Samet, Mohd Tazim Ishraque, Mehdi Ghadamyari, Krishna Kakadiya, Yash Mistry, and Youssef Nakkabi. Touchmetric: a machine learning based continuous authentication feature testing mobile applica-tion. International Journal of Information Technology, 11(4):625–631, 2019.

[2] Ingo Deutschmann, Peder Nordstr¨om, and Linus Nilsson. Continuous authentication using behavioral biometrics. IT professional, 15(4):12–15, 2013.

[3] Lei Yang, Yi Guo, Xuan Ding, Jinsong Han, Yunhao Liu, Cheng Wang, and Changwei Hu. Unlocking smart phone through handwaving biometrics. IEEE Transactions on Mobile Computing, 14(5):1044–1055, 2014.

[4] Vishal M Patel, Rama Chellappa, Deepak Chandra, and Brandon Barbello. Continuous user authentication on mobile devices: Recent progress and remaining challenges. IEEE Signal Processing Magazine, 33(4):49–61, 2016.

[5] Elaine Shi, Yuan Niu, Markus Jakobsson, and Richard Chow. Implicit authentication through learning user behavior. In Information Security: 13th International Conference, ISC 2010, Boca Raton, FL, USA, October

25- 28, 2010, Revised Selected Papers 13, pages 99–113. Springer, 2011.

[6] Elakkiya Ellavarason, Richard Guest, Farzin Deravi, Raul Sanchez-Riello, and Barbara Corsetti. Touch-dynamics based behavioural bio-metrics on mobile devices–a review from a usability and performance perspective. ACM Computing Surveys (CSUR), 53(6):1–36, 2020.

[7] Vishal M Patel, Rama Chellappa, Deepak Chandra, and Brandon Barbello. Continuous user authentication on mobile devices: Recent progress and remaining challenges. IEEE Signal Processing Magazine, 33(4):49–61, 2016.

[8] Diego Fern´andez, Vreixo Formoso, Fidel Cacheda, and Victor Carneiro. High order profile expansion to tackle the new user problem on recom-mender systems. PloS one, 14(11):e0224555, 2019.

[9] Bernhard E Boser, Isabelle M Guyon, and Vladimir N Vapnik. A training algorithm for optimal margin classifiers. In Proceedings of the fifth annual workshop on Computational learning theory, pages 144–152, 1992.