Study on Integration of FastAPI and Machine Learning for Continuous Authentication of Behavioral Biometrics

The traditional practices of security are failing slowly; new systems are needed to protect the information in the cyber world. The user authentication should be such that the systems are continuously learning and improving, and development should be fast paced without consuming too much time. The currently used continuous authentication systems have significant weaknesses in the huge data handling mechanisms including the run-time overhead taken in analyzing the user profiles. The objective of this work is to overcome these weaknesses to be able to handle multiple requests simultaneously, improve the overall performance, and decrease the cost of the behavioral biometrics-based authentication systems. In other words, we aim to create a machine learning algorithm to create user-profiles that are capable to user’s behavioral data of 64 bytes per second. The algorithm would provide over millions of user-profile recognitions per day through predictive techniques. To reach this target, we integrate the biometric behavior detection machine learning (ML) model, that doesn’t natively run on the web, with frontend using FastAPI services. These services enable the users to access the model detection using the web browser for continuous authentication using behavioral biometrics. The evaluation and the experimental results showed that the performance of the ML model by using the FastAPI has been improved by almost 45% as compared to Flask.