International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Sapien AutheiX: AI-Based Continuous Authentication Using Keystroke Dynamics for Behavioral Biometric Security |
|---|---|
| ABSTRACT | The success of continuous authentication systems based on behavioral biometrics has gained importance due to the limitations of traditional authentication methods. This work proposes a lightweight AI-based authentication system that identifies users in real-time using keystroke dynamics. Unlike multi-modal biometric systems, the proposed framework focuses on efficient feature extraction using keystroke timing elements such as dwell time and flight time. The sys-tem employs a combination of XGBoost, Support Vector Machine (SVM), and Hidden Markov Model (HMM) to achieve accurate and low-complexity authentication. Additionally, a USB or digital key-based fallback mechanism is introduced to prevent user lockouts. Experimental results demonstrate that the proposed system achieves reliable performance with reduced computational cost, making it suitable for real-time applications. |
| AUTHOR | BINGI PALLAVI, SURAMPALLI BALAKRISHNA, M. LAKSHMI APARNA BHUKTA, M. ASHFAQUE AFRIDI, DR. J. ARUNA DEVI Department of Computer Science and Engineering (DS), Anil Neerukonda Institute of Technology and Sciences, Visakhapatnam, India Associate Professor, Department of Computer Science and Engineering (DS), Anil Neerukonda Institute of Technology and Sciences, Visakhapatnam, India |
| VOLUME | 185 |
| DOI | DOI: 10.15680/IJIRCCE.2026.14060107 |
| pdf/107_Sapien AutheiX AI-Based Continuous Authentication Using Keystroke Dynamics for Behavioral Biometric Security.pdf | |
| KEYWORDS | |
| References | [1] D. D. Alves et al., “Authentication System Using Behavioral Biometrics Through Keystroke Dynamics,” IEEE. [2] J. Xiong and A. K. Belman, “Multi-Modal Adversarial Activity Detection Using Keyboard and Mouse Dynamics,” IEEE. [3] T. Chen and C. Guestrin, “XGBoost: A Scalable Tree Boosting System,” ACM SIGKDD. [4] C. Cortes and V. Vapnik, “Support-vector networks,” Machine Learning. [5] L. R. Rabiner, “A tutorial on hidden Markov models,” Proc. IEEE. [6] B. Li et al., “Wrist in Motion: Continuous Authentication Framework,” IEEE TBIOM. [7] J. Dybczak and P. Nawrocki, “Continuous Authentication on Mobile Devices,” IEEE CCGrid. [8] L. Szila´gyi et al., “Mouse Dynamics for User Identity Authentication,” IEEE LINDI. [9] M. Killourhy and R. Maxion, “Anomaly Detection for Keystroke Dynamics,” IEEE DSN. [10] F. Monrose and A. Rubin, “Keystroke Dynamics as a Biometric,” FGCS. [11] S. Mondal and P. Bours, “Continuous Authentication Using Mouse Dynamics,” IEEE TIFS. [12] M. Mare et al., “ZEBRA: Bilateral Recurring Authentication,” IEEE S&P. [13] A. Buriro et al., “Smartphone Sensor-Based Behavioral Authentication,” ICISC. [14] H. Hu et al., “Adversarial Attacks Against Mouse Dynamics Authentication,” ACM CCS. [15] G. Shen et al., “Benchmark Study on Mouse Dynamics-Based Authentication,” IEEE TIFS. |
