Enhancing Data Security Through Cryptographic Transformation Using a Graph CNN and LSTM Based Model

These days, with more and more people using the internet, cloud computing, and other types of networked information systems, protecting people's and companies' privacy and security is crucial. Looking at it this way, encryption is a sort of efficient technology that can secure the transport of public information and hence satisfy these demands. The researchers achieved their objectives by making use of a wide variety of encryption methods tailored to the requirements of this area. In order to safeguard sensitive data while minimizing the possibility of assaults, it also focused on complex mathematical challenges to create an extremely complex encrypted communication mechanism. The proposed method consists of three phases, which are preprocessing, feature selection, and model training. The formulation of the sample data and group data is necessary to establish the model's setup prior to primary processing. When reducing the dimensionality of a dataset for feature selection, Principal Component Analysis (PCA) is often used. The model was trained using the GCNN-LSTM. On average, our suggested model has a 95.33% accuracy rate, which is better than competing methods such as GCNN and CNN.