You are the key: Generating cryptographic keys from voice biometrics
Bibliographic record
Abstract
In this work we apply randomized biometric templates (RBTs) to voice biometrics by performing an experiment using speech samples from the TI46 database. Additionally, we present a novel algorithm for extracting reliable features from voice biometrics and analyze the resulting entropy of the cryptographic keys generated by the RBT algorithm. We evaluate our implementation by analyzing the number of guesses required by a powerful adversary to generate a user's cryptographic key when given access to the user's decrypted template and population statistics. Furthermore, we compare our results to the results of prior work. We demonstrate that RBTs are able to generate cryptographic keys with at least 30 bits of entropy for 36% of the population and at least 40 bits of entropy for 7% of the population, while keys generated using prior work only contain at least 20 bits of entropy for 19% of the population. We also demonstrate that RBT generated keys are able to achieve a maximum entropy of 51 bits, while keys generated using prior work are only able to achieve a maximum entropy of 26 bits.
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 | 0.011 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.003 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".