Two-factor user authentication with the CogRAM weightless neural net

The application of the Cognitive RAM (CogRAM) weightless neural net in testing a keystroke biometrics user authentication system for a numeric keypad is discussed in this paper. The two-factor user authentication system developed here uses the common password that is complemented with the keystroke patterns of the users. The keystroke pattern is represented by the force applied to constitute a fixed length passkey to compose a complete pattern for the entered password. The system has been designed and developed around an 8-bit microcontroller, based on the AVR enhanced RISC architecture. The preliminary experimental results showed that the designed system can successfully authenticate the unique and consistent keystroke biometric patterns of the users.