# Malicious Speech Classification on Internal Speech Safety Dataset (test)

Source: [Malicious Speech Classification on Internal Speech Safety Dataset (test)](<https://www.sota2.com/research/sota/malicious-speech-classification-on-internal-speech-safety-dataset-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-10T06:40:09.209Z

Evaluation of model performance for Malicious Speech Classification on the test split of the Internal Speech Safety Dataset, measured using Accuracy, F1 Score, ROC-AUC, and error rates.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Malicious Speech Classification |
| Dataset (including any stated split) | Internal Speech Safety Dataset (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 1 of 1 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Accuracy](<https://www.sota2.com/research/sota/malicious-speech-classification-on-internal-speech-safety-dataset-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/malicious-speech-classification-on-internal-speech-safety-dataset-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [Precision](<https://www.sota2.com/research/sota/malicious-speech-classification-on-internal-speech-safety-dataset-test.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall (Sensitivity)](<https://www.sota2.com/research/sota/malicious-speech-classification-on-internal-speech-safety-dataset-test.md?metric=Recall%20(Sensitivity)>): Higher is better; unit: PERCENT.

- [ROC-AUC](<https://www.sota2.com/research/sota/malicious-speech-classification-on-internal-speech-safety-dataset-test.md?metric=ROC-AUC>): Higher is better; unit: PERCENT.

- [False Negative Rate (FNR)](<https://www.sota2.com/research/sota/malicious-speech-classification-on-internal-speech-safety-dataset-test.md?metric=False%20Negative%20Rate%20(FNR)>): Lower is better; unit: PERCENT.

- [False Positive Rate (FPR)](<https://www.sota2.com/research/sota/malicious-speech-classification-on-internal-speech-safety-dataset-test.md?metric=False%20Positive%20Rate%20(FPR)>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| VoiceSHIELD-Small | 99.16 | Not recorded | 69afa58c2d603e6de3e43ad9 |

### VoiceSHIELD-Small

Accuracy: 99.16. Result ID: 69afbc146dbb7075b9576fe2.

[Reporting paper](<https://www.sota2.com/research/paper/69afa58c2d603e6de3e43ad9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69afa58c2d603e6de3e43ad9.md>)

Recorded evaluation configuration: {"Threshold":"0.2"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
