Encryption and Decryption with Space Transformation for Bi-directional Association

Most algorithms developed for encryption and decryption on network information security are focused on logic analysis. However, they are complicated to implement as a system and are difficult to be applied in a widespread manner. Recently, biomimetic-based architecture of artificial neural network was proposed to improve the reliability and performance of encryption methods such as back-propagation and overloaded Hopfield neural network. But the limitations of encryption capacity, complexity and data integrity after decryption as well as reliability are still unsolved items. This paper proposes a new algorithm to improve the reliability and efficiency of encryption and decryption with reformed bi-directional association memory (BAM) model to reduce spurious states and data separation caused by former local minima information analysis based on the Hebbian learning rule. The space transformation was used to escape crosstalk and noise vector caused by spurious states, to maintain the completeness of processed information in addition to enhancing its security. A MATLAB simulation model was used to testify the performance of reformed BAM cryptosystem.