The present disclosure relates to a behavioral biometric based authentication system. User device sends user data associated with a user to a system. The user data includes behavioral biometric data such as keystroke dynamics, mouse movements, touchscreen interactions, voice patterns, device handling and the like. The system identifies a disability based on the user data and extracts a pre-trained model associated with that specific disability from any one of: database and model repository. The model is further trained using the user data to generate and store a user profile. The user sends an authentication request during processing of a user request, the processor extracts the user profile to verify the identity of the user. Further, the anomaly detector checks for any anomalies during the processing of user request. The system sends alerts to the user device and/or temporarily locks an account and terminates the processing of the user request upon detection of an anomaly.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
ARORA, SAHIL, "EQUALAUTH: FAIR AND SECURE BIOMETRICS FOR ALL ABILITIES", Technical Disclosure Commons, (September 20, 2023)