A Trust-Enhanced Security Architecture for Authenticating Customer Records in Banking Institutions

Year : 2026 | Volume : 14 | Issue : 01 | Page : 16 22
    By

    Mahimn B. Pandya,

  • Gaurang M. Bhatt,

  1. Assistant Professor, Department of Computer science, Smt. K.B. Parekh College of Computer Science, Mahuva, Bhavnagar M.K. Bhavnagar University, Bhavnagar, Gujarat, India
  2. Assistant Professor, , Department of Computer Science, Shree Swaminarayan College of Computer Science, Sardarnagar, Bhavnagar M.K. Bhavnagar University, Bhavnagar, Gujarat, India

Abstract

The growing digital disruption of banking and financial services has completely altered the face of customer onboarding, money transactions, and financial service deliveries. Even as digital technologies provide unparalleled levels of efficiency and accessibility for consumers of financial services, they have also presented new challenges that are equally daunting. Among the growing number of financial threats that digital technology has spawned is the risk of synthetic identity fraud. Unlike identity theft, which has long been associated with financial risk in the digital era, the use of artificial identities that combine real identity data with fake demographic data is even more difficult for financial institutions to detect. Recent research has increasingly advocated blockchain-based identity management solutions due to their immutability and decentralized trust properties. However, despite their theoretical strengths, blockchain systems present critical practical limitations in real-world banking environments, including scalability constraints, high operational overhead, data privacy conflicts, governance challenges, regulatory incompatibility, and difficulties in integration with legacy core banking systems. These limitations raise a fundamental question: Is blockchain truly necessary for ensuring customer identity integrity and fraud prevention? This research answers the question posed above by proposing a complete non-blockchain solution for the prevention of synthetic identity fraud on genuine bank customers. The proposed solution combines the concept of data integrity using cryptographic techniques, multi-factor identity verification procedures, machine learning techniques for anomaly identification, and continuous monitoring under a fully secure central architecture. A system-level architecture description for a hierarchical system that includes identity verification procedures like onboarding, attribute validation checks, document and biometric verification checks, cryptographic sealing of identities, and adaptive fraud risk evaluation is proposed. A mathematical identity confidence model is developed, by which many verification scores are combined into one trust metric that supports rigorous decision-making. The experimental evaluation has been done using simulated and semi-synthetic data sets, indicating that the proposed approach significantly enhances detection accuracy and reduces false alarms with respect to traditional rule-based systems. The proposed framework provides a scalable, explainable, and deployment-ready solution suitable for modern banking ecosystems.

Keywords: Digital identity verification, financial cybersecurity, non-blockchain data integrity, secure customer records, synthetic identity fraud

[This article belongs to Journal Of Network security ]

How to cite this article:
Mahimn B. Pandya, Gaurang M. Bhatt. A Trust-Enhanced Security Architecture for Authenticating Customer Records in Banking Institutions. Journal Of Network security. 2026; 14(01):16-22.
How to cite this URL:
Mahimn B. Pandya, Gaurang M. Bhatt. A Trust-Enhanced Security Architecture for Authenticating Customer Records in Banking Institutions. Journal Of Network security. 2026; 14(01):16-22. Available from: https://journals.stmjournals.com/jons/article=2026/view=237428


References

  1. Zhang CJ, Gill AQ, Liu B, Anwar MJ. AI-based identity fraud detection: A systematic review. [Preprint]. 2025. arXiv:2501.09239. doi:10.48550/arXiv.2501.09239
  2. Wang W, Zhang J, Li Q, Zong C, Li Z. Are you for real? Detecting identity fraud via dialogue interactions. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP); 2019 Nov; Hong Kong, China. Association for Computational Linguistics; 2019. p. 1762–1771. doi:10.18653/v1/D19-1185.
  3. Borketey B. Real-time fraud detection using machine learning. J Data Anal Inf Process. 2024;12:189–209. doi:10.4236/jdaip.2024.122011.
  4. Pakina AK, Kejriwal D, Goel A, Pujari TD. AI-generated synthetic identities in fintech: Detecting deepfake KYC fraud using behavioral biometrics. IOSR J Comput Eng. 2023;25(3):26–37.
  5. Igba E, Olarinoye HS, Nwakaego VE, Sehemba DB, Oluhaiyero YS, Okika N. Synthetic data generation using generative AI to combat identity fraud and enhance global financial cybersecurity frameworks. Int J Sci Res Mod Technol. 2025;4(2):1–19. doi:10.5281/zenodo.14928919.
  6. Mungai R. Synthetic identity fraud: A critical primary national security priority. SSRN Electron J. 2024. doi:10.2139/ssrn.4770398.
  7. Awosika T, Shukla RM, Pranggono B. Transparency and privacy: The role of explainable AI and federated learning in financial fraud detection. IEEE Access. 2024;12:64551–64560. doi:10.1109/ACCESS.2024.3394528.
  8. Iqbal A, Iqbal A, Ahmed E, Rahman A, Ontor MRH. Enhancing fraud detection and anomaly detection in retail banking using generative AI and machine learning models. Am J Eng Technol. 2024;6(11):78–91. doi:10.37547/tajet/Volume06Issue11-09.
  9. Dixit S. Generative AI-powered document processing at scale with fraud detection for large financial organizations. Int J Sci Res Comput Sci Eng Inf Technol. 2024;10(5):1057–1084. doi:10.32628/CSEIT2410612455.
  10. Chitraju S. Artificial intelligence in detecting synthetic identity fraud. SSRN. 2025. doi:10.2139/ssrn.5353731.
  11. Anasuri S. Synthetic identity detection using graph neural networks. Int J Artif Intell Data Sci Mach Learn. 2023;4(4):87–96.
  12. Liu J, Huang W, Li T, Ji S, Zhang J. Cross-domain knowledge graph chiasmal embedding for multi-domain item–item recommendation. IEEE Trans Knowl Data Eng. 2022;35(5):1–1. doi:10.1109/TKDE.2022.3151986.
  13. Riccio D, Galdi C, Manzo R. Biometric/cryptographic keys binding based on function minimization. 2016 12th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), Naples, Italy. 2016. p. 144–150. doi:10.1109/SITIS.2016.31.
  14. Crosby SA, Wallach DS. Efficient data structures for tamper-evident logging. In: Proceedings of the 18th USENIX Security Symposium (SSYM ’09); 2009; Montreal, Canada. USENIX Association; 2009. p. 317–334.
  15. Pandya M, Joshi H, Jani A. A novel digital watermarking algorithm using random matrix image. Int J Comput Appl. 2013;61:18–21. doi:10.5120/9900-4481.
  16. Pandya M, Joshi H, Jani A. A bespoke technique for secret messaging. Int J Comput Netw Inf Secur. 2013;5:40–46. doi:10.5815/ijcnis.2013.05.05.
  17. Pandya M, Jani A. A novel algorithm for information hiding. Int J Adv Res Comput Sci. 2018;9(2):7–10. doi:10.26483/ijarcs.v9i2.5489.
  18. Pandya M, Jani A. A hybrid approach for secure message communication and color image watermarking. Elixir Digit Process. 2018;114:49488–49491.
Regular Issue Subscription Original Research
Volume 14
Issue 01
Received 18/12/2025
Accepted 28/12/2025
Published 20/02/2026
Publication Time 64 Days
53

Login


My IP

PlumX Metrics