Y. Chitti Babu; Rashmi V.; Divvela Srinivasa Rao; Narendra Babu Pamula; M. Lakshmi Narayana; S. Sagar Imambi

Secure Federated Next-Word Prediction Using Dual-Factor Authentication

PDF (670KB), PP.250-263

Views: 0 Downloads: 0

Author(s)

Y. Chitti Babu ¹ Rashmi V. ² Divvela Srinivasa Rao ³ Narendra Babu Pamula ^4,* M. Lakshmi Narayana ⁵ S. Sagar Imambi ⁶

1. St. Ann’s College of Engineering and Technology, Bapatla District, Andhra Pradesh, 522102, India

2. Department of Information Technology, Prasad V Potluri Siddhartha Institute of Technology, Vijayawada, Andhra Pradesh, 520007, India

3. Department of AI & DS, Lakireddy Bali Reddy College of Engineering, Mylavaram, Krishna District, Andhra Pradesh, 521230, India

4. Department of Department of CSE, Koneru Lakshmaiah Educational Foundation, Guntur, Andhra Pradesh, 522302, India

5. Department of Information Technology, S.R.K.R Engineering College, China Amiram, Bhimavaram West Godavari District, Andhra Pradesh, 534204, India

6. Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Guntur, Andhra Pradesh, 522302, India

* Corresponding author.

DOI: https://doi.org/10.5815/ijwmt.2026.05.15

Received: 16 Jun. 2026 / Revised: 13 Jul. 2026 / Accepted: 15 Aug. 2026 / Published: 8 Oct. 2026

Index Terms

Data privacy, Decentralized Learning, LSTM networks, Two-step Authentication, Aggregation, Homogeneous FL environment

Abstract

Federated Learning (FL) has become a promising distributed machine learning paradigm that allows collaborative model training while maintaining user privacy by keeping sensitive data on local devices. However, existing FL-based next-word prediction systems mainly focus on the model performance and lack robust mechanisms to prevent unauthorized users and compromised devices from joining the training process, raising security and reliability issues. To overcome this limitation, in this paper, a secure homogeneous federated learning framework for next-word prediction is proposed by combining a Long Short-Term Memory (LSTM) model with a dual-factor authentication mechanism. The proposed framework includes a central aggregation server and three homogeneous client devices with the same model architecture and training configurations to ensure stable convergence and consistent learning. The dual-factor authentication mechanism integrates the OTP-based user authentication and device authentication to guarantee that only legitimate users and trusted devices can join in the collaborative training. The main metrics for experimental evaluation were prediction accuracy, convergence speed, and security performance. The proposed framework achieved prediction accuracies of ~100%, ~100%, and ~98% across the three participating clients after 50 training epochs, showing faster convergence and more stable learning than a conventional federated learning baseline. Moreover, the authentication mechanism successfully resists unauthorized access with low computational and communication overhead. The results demonstrate that the proposed framework not only improves the accuracy and security of federated next-word prediction but also enhances the trustworthiness, reliability, and practical deployment of privacy-preserving language prediction systems in distributed edge environments.

Cite This Paper

Y. Chitti Babu, Rashmi V., Divvela Srinivasa Rao, Narendra Babu Pamula, M. Lakshmi Narayana, S. Sagar Imambi, "Secure Federated Next-Word Prediction Using Dual-Factor Authentication", International Journal of Wireless and Microwave Technologies(IJWMT), Vol.16, No.5, pp. 250-263, 2026. DOI:10.5815/ijwmt.2026.05.15

Reference

[1]Ambulgekar S. Next Words Prediction Using Recurrent Neural Networks. ITM Web Conf. 2021;40:03034. https://doi.org/10.1051/itmconf/20214003034
[2]Long G, Xie M, Shen T, Zhou T, Wang X, Jiang J, Zhang C. Multi-Center Federated Learning: Clients Clustering for Better Personalization. arXiv. 2020. https://arxiv.org/abs/2005.01026
[3]McMahan HB, Moore E, Ramage D, Agüera y Arcas B. Federated Learning of Deep Networks using Model Averaging. arXiv. 2016. https://arxiv.org/pdf/1602.05629v1.pdf
[4]Jiang H, Liu M, Yang B, et al. Customized Federated Learning for Accelerated Edge Computing with Heterogeneous Task Targets. Comput Netw. 2020. https://www.sciencedirect.com/science/article/pii/S1389128620312135
[5]Liu Y, Kang Y, Xing C, Chen T, Yang Q. A Secure Federated Transfer Learning Framework. IEEE Intell Syst. 2020;35(4):70–82. https://doi.org/10.1109/MIS.2020.2988525
[6]Gong M, Feng J, Xie Y. Privacy-Enhanced Multi-Party Deep Learning. Neural Netw. 2020;121:484–496. https://doi.org/10.1016/j.neunet.2019.10.001
[7]Abadi M, Chu A, Goodfellow I, et al. Deep Learning with Differential Privacy. arXiv. 2016. https://arxiv.org/abs/1607.00133
[8]Yurochkin M, Agarwal M, Ghosh S, Greenewald K, Hoang T, Khazaeni Y. Bayesian Nonparametric Federated Learning of Neural Networks. arXiv. 2019. https://arxiv.org/abs/1905.12022
[9]Lindell Y, Pinkas B. A Proof of Security of Yao's Protocol for Two-Party Computation.. Journal of Cryptology. 2009;22(2):161–188. https://doi.org/10.1007/s00145-008-9036-8
[10]Geyer RC, Klein T, Nabi M. Differentially Private Federated Learning: A Client Level Perspective. arXiv. 2018. https://arxiv.org/abs/1712.07557
[11]Nishio T, Yonetani R. Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge. arXiv. 2018. https://arxiv.org/abs/1804.08333
[12]Li T, Sahu AK, Talwalkar A, Smith V. Federated Optimization in Heterogeneous Networks. Proc Mach Learn Syst. 2020;2:429–450. https://proceedings.mlsys.org/paper_files/paper/2020/file/1f5fe83998a09396ebe6477d9475ba0c-Paper.pdf
[13]Huang J, Rui Z, Kang L. Fedisp: An Incremental Subgradient-Proximal-Based Ring-Type Architecture for Decentralized Federated Learning. Complex Intell Syst. 2024; 10:2499–2514. https://doi.org/10.1007/s40747-023-01272-4
[14]Pamula NB, Khan AK, Sarkar A. Development of Efficient Protocols for the Secure Transmission of Training Parameters in a Federated Network Using Elliptic Curve Cryptography. J Theor Appl Inf Technol. 2025;103(2):384–399. https://doi.org/10.5281/zenodo.15761904
[15]Pamula NB, Khan AK, Sarkar A. Mobile OTP Authentication Protocol Design and Implementation for Local Federated Clients to Federated Central Server via MQTT. Int J Inf Technol Comput Sci. 2026;18(2):202–221. https://doi.org/10.5815/ijitcs.2026.02.12
[16]Sattler F, Wiedemann S, Müller K-R, Samek W. Robust and Communication-Efficient Federated Learning from Non-IID Data. IEEE Trans Neural Netw Learn Syst. 2021.https://arxiv.org/pdf/1903.02891
[17]Karimireddy SP, Kale S, Mohri M, Reddi SJ, Stich SU, Suresh AT. SCAFFOLD: Stochastic Controlled Averaging for Federated Learning. Proc Int Conf Mach Learn. 2020; 119:5132–5143. http://proceedings.mlr.press/v119/karimireddy20a.html
[18]Li Y, Fard KG. Federated Edge Intelligence for Carbon Emission Forecasting Using Deep Neural Networks: A Privacy-Preserving Approach. J Cloud Comput. 2026; 15:57. https://doi.org/10.1186/s13677-026-00877-7
[19]Khan Y, Sánchez D, Domingo-Ferrer J. Federated Learning-Based Natural Language Processing: A Systematic Literature Review. Artif Intell Rev. 2024; 57:320. https://doi.org/10.1007/s10462-024-10970-5
[20]Zhang H, Shafiq MO. Survey of Transformers and Towards Ensemble Learning Using Transformers for Natural Language Processing. J Big Data. 2024; 11:25. https://doi.org/10.1186/s40537-023-00842-0
[21]Hussain S, Sohail M, Khan NA. SEMFED: Semantic-Aware Resource-Efficient Federated Learning for Heterogeneous NLP Tasks. arXiv. 2025.https://arxiv.org/abs/2505.23801

International Journal of Wireless and Microwave Technologies (IJWMT)