DNA Cryptography and Deep Learning using Genetic Algorithm with NW algorithm for Key Generation.

Area of Science:

• Computer Science
• Bioinformatics
• Cryptography

Background:

• Cryptography relies on complex mathematics for secure data transmission.
• Current DNA-based cryptography implementations are limited to laboratory settings and are costly.
• There is a need for efficient digital-level algorithms for DNA computing in cryptography.

Purpose of the Study:

• To introduce DNA Deep Learning Cryptography, a novel technique combining DNA sequences and deep learning for data concealment.
• To propose easy and effective algorithms for digital-level DNA computing in cryptography.
• To develop a robust key generation method and an encryption/decryption process.

Main Methods:

• Key generation using a Genetic Algorithm with the Needleman-Wunsch algorithm, inspired by natural selection.
• Encryption and decryption implemented using DNA computing principles: Transcription, Translation, and DNA Sequencing.
• Integration of Deep Learning models to enhance the cryptographic process.

Main Results:

• Development of a novel cryptographic technique, DNA Deep Learning Cryptography.
• Proposed algorithms facilitate digital-level implementation of DNA computing for encryption.
• Successful integration of biological operations and deep learning for secure data handling.

Conclusions:

• DNA Deep Learning Cryptography offers a promising approach for secure data concealment.
• The proposed methods enable efficient and accessible digital implementation of DNA-based cryptographic techniques.
• This research bridges the gap between theoretical DNA computing and practical cryptographic applications.