Unimodal Touch Behaviour-Based User Authentication Using Deep Learning and Swarm Intelligence for Smartphones
DOI:
https://doi.org/10.13052/jmm1550-4646.2224Keywords:
Continuous authentication, touch biometrics, mobile security, deep learning, swarm intelligenceAbstract
Smartphones have become necessary in everyday life since they make communication, financial transactions, and data access easier. However, their broad use poses serious security risks, especially regarding ongoing user authentication. Traditional authentication techniques, including PINs, passwords, and patterns, only authenticate users at points of entry, leaving devices open to replay attacks, session hijacking, and spoofing. To overcome these constraints, the hybrid authentication approach proposed in this research uses multimodal touch behaviour for real-time identity verification. Using the Touchalytics dataset, this method combines motion sensor data from accelerometers, gyroscopes, and magnetometers with fine-grained touch attributes, including touch area, pressure, finger orientation, and typing dynamics. Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks are combined in the system’s deep learning (DL) architecture for sequential touch analysis, and optimization approaches are used to improve model performance. The model captures detailed touch behaviour and motion sensor data, with hyperparameter tuning applied using Particle Swarm Optimization (PSO), Cuckoo Search Optimization (CSO), and Sea-Horse Optimization (SHO). The CNN-LSTM + PSO model outperforms standalone DL models by achieving 99.86% accuracy with a False Acceptance Rate (FAR) of 0.0009, False Rejection Rate (FRR) of 0.0012, and Equal Error Rate (EER) of 0.001, according to extensive assessment on the Touchalytics dataset. For next-generation mobile security, this combination of Swarm Intelligence (SI) and DL provides a strong, flexible, and effective authentication architecture.
Downloads
References
Statista, “Number of Smartphone Users Worldwide According to 2025 Report.” [Online] Available: https://www.statista.com/outlook/cmo/consumer-electronics/telephony/smartphones/worldwide.
GSMA, “The Mobile Industry Impact Report: Sustainable Development Goals Executive Summary 2024.” [Online] Available: https://www.gsma.com/solutions-and-impact/connectivity-for-good/mobile-economy/wp-content/uploads/2024/02/260224-The-Mobile-Economy-2024.pdf.
Juniper, “Digital Banking Users to Reach 2 Billion This Year, Representing Nearly 40% of the Global Adult Population.” [Online] Available: https://www.juniperresearch.com/press/digital-banking-users-reach-nearly-3-billion-2021.
A Bajaber, MA Fadel and LA Elrefaei (2022) “Evaluation of Deep Learning Models for Person Authentication Based on Touch Gesture.” Comput. Syst. Sci. Eng., 42(2), 465–481.
Hassan et al. (2022) “Continuous User Authentication Using Touch Biometrics And Machine Learning: A Survey.” Journal of Network and Computer Applications, 203, 103314.
Alyahya et al. (2020) “Continuous Authentication Using Ensemble Learning For Mobile Touch Biometrics.” Sensors, 20(8), 2298.
Jiang et al. (2022) “Touch Dynamics-Based Continuous Authentication With User-Adaptive Threshold.” Sensors, 22(3), 820.
KK Verma, BM Singh and A Dixit (2022) “A Review Of Supervised And Unsupervised Machine Learning Techniques For Suspicious Behaviour Recognition In Intelligent Surveillance Systems.” Int. J. Inf. Tecnol., 14, 397–410.
Y Gao, Y Jia and Y Zhao (2019) “A Privacy-Preserving Continuous Authentication System Using Touch Biometrics.” IEEE Transactions on Information Forensics and Security, 14(12), 3324-3337.
HT Nguyen, TT Nguyen and HT Nguyen (2022) “Mobile Crowd-Sourced Data Fusion And Urban Traffic Estimation.” Journal of Mobile Multimedia, 18(3–4), 455–472.
M Gayathri and C Malathy (2022) “A Deep Learning Framework For Intrusion Detection And Multimodal Biometric Image Authentication.” Journal of Mobile Multimedia, 18(2), 393–420.
S Bajaber, I Khalil and M Khreich (2021) “A Comparative Study Of Deep Learning Architectures For Continuous Authentication Using Touch Dynamics.” Security and Communication Networks, 2021, 1–12.
H Feng, J Zhao, J Yan, Y Zhou and X Li (2018) “Continuous Mobile Authentication Using Touchscreen Biometrics: A Deep Learning Approach.” ACM Transactions on Information Systems (TOIS), 36(3), 1–20.
Y Gao, J Zhao, X Li and X Yuan (2016) “Continuous Authentication Using Touchscreen Gestures On Mobile Devices.” IEEE Transactions on Mobile Computing, 15(12), 3052–3065.
S Li, X Lin, Y Sun and X Deng (2018) “Continuous Authentication For Mobile Devices Using Multi-Modal Touch Dynamics.” Computers & Security, 77, 828–842.
Y Xu, X Chen, J Zhao, X Li and D Kong (2015) “Unsupervised Continuous Authentication Using Touch Biometrics.” IEEE Transactions on Information Forensics and Security, 10(9), 1871–1883.
B Traore, SU Hassan, AH Abdullah and F Saeed (2018) “Continuous Authentication Using Touch Velocity On Mobile Devices.” 2018 International Conference on Computing and Artificial Intelligence (ICCAI), 1–6.
SU Hassan, B Traore, AH Abdullah and F Saeed (2020) “A Convolutional Neural Network-Based Approach For Continuous Authentication Of Mobile Users Using Touch Patterns.” 2020 IEEE 17th International Conference on Smart Communities (SC), 1–7.
AS Eesa, B Traore and AH Abdullah (2019) “Continuous Authentication Of Mobile Users Using Touch Pressure.” Journal of Physics: Conference Series, 1144(1), 012022.
Z DeRidder, N Siddiqui, T Reither, R Dave, B Pelto, N Seliya and M Vanamala (2022) “Continuous User Authentication Using Machine Learning and Multi-Finger Mobile Touch Dynamics with a Novel Dataset.” 2022 9th International Conference on Soft Computing & Machine Intelligence (ISCMI), Toronto, ON, Canada, 42–46.
B Pelto, M Vanamala and R Dave (2023) “Your Identity is Your Behaviour—Continuous User Authentication Based on Machine Learning and Touch Dynamics.” 2023 3rd International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), Tenerife, Canary Islands, Spain, 1–6.
L Pryor, R Dave and N Seliya (2022) “Deep Learning and Machine Learning, Better Together Than Apart: A Comprehensive Review on Mobile Authentication.” Journal of Cybersecurity and Privacy, 3(2), 331–354.
X Zhang, S Li and K Zhao (2020) “A Bezier Curve-Based Feature Extraction Method For Touch Biometrics.” Sensors, 20(17), 4823. https://www.mdpi.com/1424-8220/20/17/4823.
Zheng et al. (2019) “An Attention-Based Deep Learning Approach For Continuous Authentication Using Touch Biometrics.” IEEE Transactions on Information Forensics and Security, 14(1), 184–195. http://ieeexplore.ieee.org/document/9121981.
M Frank (n.d.) “Touchalytics: Touch-Based Authentication On Mobile Devices.” [Online] Available: https://www.mariofrank.net/touchalytics/.
Y Kim, S Eum and J Choo (2020) “Continuous Authentication On Touchscreens Using Time-Dependent Features.” Sensors, 20(17), 4888.
W Li, R Wang and B Xu (2019) “Enhancing Security And Privacy In Touch Biometric Authentication.” Sensors, 19(17), 3847.
O Akintunde, A Adetunji, O Fenwa, J Oguntoye, D Olayiwola and A Adeleke (2025) “Comparative Analysis Of Score Level Fusion Techniques In Multi-Biometric System.” LAUTECH Journal of Engineering and Technology, 19(1), 128–141.
A Gupta, P Singh, D Jain, AK Pandey, A Jain and G Sharma (2022, January) “Real-Time Exhaustion Detection by Image Classification Using Deep Convolution Neural Network.” International Conference on Electrical and Electronics Engineering (pp. 482–491), Springer Singapore.
J Hu (2025) “Online Criminal Behaviour Recognition Based on CNNH and MCNN-LSTM.” Informatica, 49(12).
A Mullai and K Mani (2021) “Enhancing The Security In RSA And Elliptic Curve Cryptography Based On Addition Chain Using Simplified Swarm Optimization And Particle Swarm Optimization For Mobile Devices.” Int. J. Inf. Tecnol., 13, 551–564. https://doi.org/10.1007/s41870-019-00413-8.
D Wang, D Tan and L Liu (2018) “Particle Swarm Optimization Algorithm: An Overview.” Soft Computing, 22, 387–408.
AS Joshi, O Kulkarni, GM Kakandikar and VM Nandedkar (2017) “Cuckoo Search Optimization Review.” Materials for Today: Proceedings, 4(8), 7262–7269.
EH Houssein, MR Saad, E Çelik, G Hu, AA Ali and H Shaban (2024) “An Enhanced Sea-Horse Optimizer For Solving Global Problems And Cluster Head Selection In Wireless Sensor Networks.” Cluster Computing, 27(6), 7775–7802.
