DeepRL-ID: Scalable End-to-End Deep Reinforcement Learning for Dynamic Real-Time Identity Validation
Keywords:
Deep Reinforcement Learning, Identity Validation, Multimodal Biometrics, Real-Time Authentication, Recognition Rate, Robustness, ScalabilityAbstract
Real-time identity verification in high-throughput digital ecosystems demands adaptive, sequential decision-making under uncertainty. Traditional rule-based or static supervised models often fail to generalize under evolving user behaviors or adversarial strategies. This research introduces DeepRL-ID, a scalable end-to-end deep reinforcement learning framework for dynamic real-time identity validation. The framework formulates the verification process as a Markov Decision Process (MDP), where an autonomous agent optimizes authentication policies by integrating multi-modal identity signals, including biometric embeddings, behavioral telemetry, and transactional metadata. The architecture employs Deep Q-Networks (DQN) with prioritized experience replay, hierarchical action abstraction, and distributed experience sharing to navigate high-dimensional state spaces efficiently. DeepRL-ID proactively adapts to sequential and evolving adversarial threats, learning to flag suspicious patterns before breaches occur. Empirical evaluation on large-scale identity datasets demonstrates substantial improvements in verification accuracy, latency, and system throughput compared to conventional static and supervised baselines, while maintaining robust generalization to previously unseen identity patterns. These results establish deep reinforcement learning as a practical, adaptive, and scalable methodology for operational identity validation in complex and adversarial digital ecosystems.
Downloads
References
Batool, S., S. A. Gill, S. Javaid, and A. J. Khan, “Good governance via e-governance: Moving towards digitalization for a digital economy,” Review of Applied Management and Social Sciences, vol. 4, no. 4, pp. 823–836, 2021.
Papernot, N., et al., “Adversarial examples in machine learning,” in Proc. IEEE European Symp. Security and Privacy, 2017.
Das, R., Adopting Biometric Technology: Challenges and Solutions. London, U.K.: Routledge, 2017.
Kumar, S., and S. Prasanna, “Heterogeneous ensemble learning for robust adversarial pattern recognition in digital ecosystems,” Journal of Computational Analysis and Applications, vol. 27, no. 5, pp. 18–28, 2019.
Hamidi, H., “An approach to develop smart health using Internet of Things and authentication based on biometric technology,” Future Generation Computer Systems, vol. 91, pp. 434–449, 2019.
Kumar, S., S. Prasanna, and X. Ruan, “A unified hybrid machine learning architecture for robust identity anomaly detection in large-scale digital ecosystems,” Journal of Electrical Systems, vol. 14, no. 1, pp. 160–173, 2018.
Bock, L., Identity Management with Biometrics: Explore the Latest Innovative Solutions to Provide Secure Identification and Authentication. Birmingham, U.K.: Packt Publishing, 2020.
S. K. S. Prasanna, “GeoDNN: Geometry-aware deep neural networks for cross-domain fingerprint spoof detection,” Int. J. Intell. Syst. Appl. Eng., vol. 6, no. 1, pp. 97–107, Mar. 2018.
Ciolacu, M., A. F. Tehrani, L. Binder, and P. M. Svasta, “Education 4.0—Artificial intelligence assisted higher education: Early recognition system with machine learning to support students' success,” in Proc. IEEE 24th Int. Symp. Design and Technology in Electronic Packaging (SIITME), Oct. 2018, pp. 23–30.
Sundararajan, K., and D. L. Woodard, “Deep learning for biometrics: A survey,” ACM Computing Surveys, vol. 51, no. 3, pp. 1–34, 2018.
Zhang, X., L. Yao, C. Huang, T. Gu, Z. Yang, and Y. Liu, “DeepKey: An EEG and gait based dual-authentication system,” arXiv preprint arXiv:1706.01606, 2017.
Zou, Q., Y. Wang, Q. Wang, Y. Zhao, and Q. Li, “Deep learning-based gait recognition using smartphones in the wild,” IEEE Trans. Inf. Forensics Security, vol. 15, pp. 3197–3212, 2020.
Mehraj, H., and A. H. Mir, “A survey of biometric recognition using deep learning,” EAI Endorsed Trans. Energy Web, vol. 8, no. 33, 2021.
Dos Santos, C. F. G., et al., “Gait recognition based on deep learning: A survey,” ACM Computing Surveys, vol. 55, no. 2, pp. 1–34, 2022.
Mekruksavanich, S., and A. Jitpattanakul, “Deep learning approaches for continuous authentication based on activity patterns using mobile sensing,” Sensors, vol. 21, no. 22, p. 7519, 2021.
López, A. B., “Deep learning in biometrics: A survey,” ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal, vol. 8, no. 4, p. 19, 2019.
Wang, M., and W. Deng, “Deep face recognition: A survey,” Neurocomputing, vol. 429, pp. 215–244, 2021.
Ashfahani, A., and M. Pratama, “Autonomous deep learning: Continual learning approach for dynamic environments,” in Proc. SIAM Int. Conf. Data Mining, May 2019, pp. 666–674.
S. K. S. Prasanna, “DeepSynth: A robust multi-layer neural detection of coordinated latent anomalies in high-dimensional identity systems,” Int. J. Intell. Syst. Appl. Eng., vol. 7, no. 1, pp. 66–77, Mar. 2019.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
