Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{203042,
        author = {Jeevan P and Manjunath Patil and Kushwith K S and Gnanesh K N},
        title = {Biometric data encryption for secure storage},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {10403-10410},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=203042},
        abstract = {Biometric authentication systems have gained significant attention in secure access control applications, yet traditional implementations face critical vulnerabilities in data storage and transmission [7]. This paper presents an advanced dual bio- metric authentication system that integrates face recognition and fingerprint verification with novel steganographic key embedding and cloud database integration. The proposed system addresses fundamental limitations of existing single-factor biometric systems by implementing a multi-layered security architecture that combines deep learning-based facial recognition using Siamese neural networks with triplet loss [14], MediaPipe-based finger- print capture [5], and cryptographic hashing techniques [10]. A key innovation lies in the steganographic embedding of biometric keys within carrier images using Least Significant Bit (LSB) manipulation, providing covert storage and transmission channels that enhance security against interception attacks [1], [3]. The system leverages MongoDB Atlas with GridFS for scalable cloud storage [8], [9], enabling secure distribution of steganographic images while maintaining data integrity. Implementation using Flask backend [11] and React frontend [12] demonstrates real- time authentication capabilities with processing times under 2 seconds. Experimental results show face recognition accuracy of 95.8% on diverse datasets and fingerprint matching precision exceeding 97%, while steganographic embedding maintains im- perceptible image quality with PSNR values above 45 dB. The integrated system successfully demonstrates enhanced security through layered biometric verification, encrypted storage, and covert key distribution, offering a robust solution for high- security authentication applications in banking, healthcare, and government sectors.},
        keywords = {biometric authentication, face recognition, fingerprint verification, steganography, cloud security, dual-factor authentication, LSB embedding, Siamese neural networks},
        month = {May},
        }