A preliminary study of factors affecting the performance of a Playback Attack Detector
Bibliographic record
Abstract
A playback attack refers to the situation when an intruder plays back a recording of a true client uttering his or her pass phrase in order to bypass a speaker verification system. Playback attacks are effective and easy to implement, thus, posing a serious threat to the security of a pass-phrase protected speaker verification system. A Playback Attack Detector (PAD) has been proposed to safeguard the speaker verification systems against playback attacks. The proposed PAD capitalizes on the hypothesis that due to the random nature of speech production process, distinctions can always be found between any two utterances. Thus, if little distinction is found between two utterances, it is likely that one utterance is the playback of the other. In this paper, the proposed PAD algorithm is summarized. The design and the collection process of a database used to evaluate the effects of different factors (e.g. client, pass phrase, playback speaker, communication channel, and number of stored recordings) on the PAD's performance is detailed. Experimental procedures used for performance evaluation are described and results are presented.
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 | 0.003 | 0.044 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".