Rubik's Encryption Combined with CNN for Biometric Authentication

Abstract

In response to the rapid evolution of technology, safeguarding user data has become paramount, necessitating a robust solution against diverse cyber threats. This research project proposes a comprehensive approach that integrates biometric authentication, specifically iris and fingerprint recognition, with a sophisticated encryption system based on Rubik's Cube and facilitated by Convolutional Neural Networks (CNNs). Biometric authentication establishes an unassailable link between data records and individuals, ensuring heightened accuracy and security. To counter potential threats, the project incorporates a resilient technique known as zero-bit watermarking, embedding minimal information without compromising the original biometric data's size or quality. The integration of Rubik's Cube-based encryption adds an additional layer of complexity to data protection, employing a dynamic and visually intricate encryption algorithm. The amalgamation of iris and fingerprint authentication leverages the unique biological characteristics of individuals, creating a multi-layered security approach. The CNNs play a pivotal role as the backbone for efficient feature extraction and authentication decision-making, enhancing the overall system's accuracy and reliability. This innovative fusion of cryptographic methods and biometric authentication offers a comprehensive solution for safeguarding sensitive information across diverse applications, from secure data storage to fortified communication channels, addressing the evolving landscape of cybersecurity challenges.