Encryption technique based on chaotic neural network space shift and color-theory-induced distortion

Area of Science:

• Computer Science
• Information Security
• Cryptography

Background:

• Information privacy is crucial for digital trust and the adoption of technologies like the semantic web and Internet of Things.
• Existing encryption methods face challenges from evolving security threats.
• There is a continuous need for advanced encryption techniques to counter emerging security challenges.

Purpose of the Study:

• To propose a novel encryption technique that enhances information privacy and security.
• To develop a computational model integrating color theory and chaotic systems for encryption.
• To create a robust method for confusing plaintext and generating complex, key-based ciphertext.

Main Methods:

• Developed a unique computational model inspired by color theory and chaotic systems.
• Implemented operations to highly confuse plaintext.
• Designed key-based mechanisms for generating complex ciphertext.
• Conducted experiments using a prototype implementation.

Main Results:

• The proposed encryption technique demonstrated high confusion of plaintext.
• Generated key-based, complex codes to obscure ciphertext effectively.
• The technique proved effective, passing rigorous NIST/ENT security tests.
• Experimental results indicated the technique is also fast in performance.

Conclusions:

• The novel encryption technique offers a promising solution for enhancing digital information privacy and security.
• The integration of color theory and chaotic systems provides a robust and efficient encryption model.
• The method's effectiveness and speed make it suitable for countering modern cybersecurity challenges.