Neural-like Methods and Hardware Structures for Real-time Data Encryption and Decryption
Ivan Tsmots, Yurii Tsymbal, Oleksa Skorokhoda, Roman Tkachenko · 2019 IEEE 14th International Conference on Computer Sciences and Information Technologies (CSIT) · 2019
Combined method of cryptographic data protection based on the autoassociative neural network using “model of successive geometric transformations” paradigm and XOR masking has been described. Improved methods of scalar product calculation with regards to hardware implementation have been presented. Structure of neural-like hardware means for real-time data encryption-decryption has been developed.