Enhancing Data Security Via the Application of Back- Propagation Feed-Forward Methods in Encryption

Abstract

The computer society uses a variety of automated methods for file security and data storage. Several organisations are concerned about the information exchange via an unsecured network for a distributed architecture, such as the time-sharing and real-time system. Probably the most crucial element that contributes to effective security is cryptography. Using a constant weighted factor for boosting the factor, the study aims at extending or updating the earlier presented Artificial Neural Network encryption model. Back-propagation feed-forward methods are a type of artificial neural network (ANN) that can be used in encryption to enhance data security. ANNs are modelled after the structure and function of the human brain and can be trained to recognize patterns and make predictions based on input data. In the context of encryption, back-propagation feed-forward methods can be used to encrypt data by converting it into a series of numerical values, which are then fed into the ANN. The ANN converts the data into an encrypted form that is challenging for unauthorised users to decode, using a series of mathematical operations. The back-propagation algorithm is used to train the ANN to recognize patterns in the input data and adjust the mathematical operations used to transform the data in order to improve the accuracy of the encryption. This allows the ANN to adapt to new types of data and improve its encryption capabilities over time. Using back-propagation feed-forward methods in encryption can provide a number of benefits for data security. For instance, it can aid in preventing unauthorised access to private information, safeguarding against data breaches, and guaranteeing the secrecy and accuracy of data transmissions. However, it is important to note that no encryption method is completely fool proof, and additional security measures may be necessary to protect against sophisticated attacks.