API Security Risk Assessment Based on Dynamic ML Models
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Adding machine learning (ML) and artificial intelligence (AI) logic models to authentication is an inevitable process. In this work, we show that the combination of qualitative and quantitative verification over model created on training data may significantly reduce false access probability, even if the user's credentials ID and password are compromised. We propose three layers of authentication based on user ID and password, silent signals, and biometrical data. The system uses supervised ML to determine the user's risk level. Basic model and associate implementation performance shows that we can, with high probability, identify an intruder based on silent signals, historical data, and behavioural biometrics. The system is compositional, so further improvement by introducing more silent signals and behavioural analytics can, theoretically, eliminate false acceptance. Whenever the risk level is higher than some threshold, an additional verification is required. The threshold may increase over time and in that case, the probability of additional verification of a legitimate user decreases.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 it