Convolutional neural network based key generation for security of data through encryption with advanced encryption standard

Machine learning techniques, especially deep learning, are playing an increasingly important role in our lives. Deep uses different models to extract information from the data. They have already had a huge impact areas such as health (i.e., cancer diagnosis), self-driving cars, speech recognition, and data encryption. Recently, models, including convolutional neural networks (CNN), been proven be more effective security field. Moreover, National Institute of Standards Technology (NIST) recommends advanced encryption standard (AES) algorithm most often utilized method several applications. In this paper, crypt-intelligent system (CIS) capable securing is proposed. It based on combination performance CNN with AES, by substituting key expansion unit AES architecture that performs generation. Our CIS described using very high-speed integrated circuit (VHSIC) hardware description language (VHDL), simulated ModelSim, synthesized, implemented Xilinx ISE 14.7. Finally, Airtex-7 series XC7A100T device has achieved throughput 965.88 Mbps. addition, offers high degree flexibility supported reconfigurability, experimental results, if sufficient resources available, can provide satisfy cryptographic