# Audio-Visual Deepfake Detection on FakeAVCeleb (EER)

Source: [Audio-Visual Deepfake Detection on FakeAVCeleb (EER)](<https://www.sota2.com/research/sota/audio-visual-deepfake-detection-on-fakeavceleb-eer>)

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

Data updated: 2026-05-04T08:37:32.585Z

Evaluation of Audio-Visual Deepfake Detection performance on the FakeAVCeleb dataset, specifically reporting the Equal Error Rate (EER).

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 | Audio-Visual Deepfake Detection |
| Dataset (including any stated split) | FakeAVCeleb |
| Metric | EER |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 4 of 4 |
| 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

- [EER](<https://www.sota2.com/research/sota/audio-visual-deepfake-detection-on-fakeavceleb-eer.md?metric=EER>): Lower is better; unit: PERCENT.

## Recorded results

| Method | EER | Result date | Report paper |
| --- | --- | --- | --- |
| W2V-300M | 5.8 | Not recorded | 69f8280dc0f56ed843088a2c |
| Alethia-Base | 6.3 | Not recorded | 69f8280dc0f56ed843088a2c |
| WavLM-Large | 7 | Not recorded | 69f8280dc0f56ed843088a2c |
| HuBERT-Large | 8.1 | Not recorded | 69f8280dc0f56ed843088a2c |

### W2V-300M

EER: 5.8. Result ID: 69f85ab247f34ce924dc16d7.

[Reporting paper](<https://www.sota2.com/research/paper/69f8280dc0f56ed843088a2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68891e209131cea1cc36.md>)

[Implementation](<https://github.com/pytorch/fairseq>)

Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot testing"}. This record does not assert independent reproduction.

### Alethia-Base

EER: 6.3. Result ID: 69f85ab247f34ce924dc16d8.

[Reporting paper](<https://www.sota2.com/research/paper/69f8280dc0f56ed843088a2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f8280dc0f56ed843088a2c.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot testing"}. This record does not assert independent reproduction.

### WavLM-Large

EER: 7. Result ID: 69f85ab247f34ce924dc16d6.

[Reporting paper](<https://www.sota2.com/research/paper/69f8280dc0f56ed843088a2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dfa1e209131cea3d210.md>)

[Implementation](<https://aka.ms/wavlm>)

Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot testing"}. This record does not assert independent reproduction.

### HuBERT-Large

EER: 8.1. Result ID: 69f85ab247f34ce924dc16d5.

[Reporting paper](<https://www.sota2.com/research/paper/69f8280dc0f56ed843088a2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a2a1e209131cea26880.md>)

[Implementation](<https://github.com/pytorch/fairseq/tree/master/examples/hubert>)

Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot testing"}. This record does not assert independent reproduction.

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