Study on Integration of FastAPI and Machine Learning for Continuous Authentication of Behavioral Biometrics
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".