# Face Anti-Spoofing on CASIA-RFS (test)

Source: [Face Anti-Spoofing on CASIA-RFS (test)](<https://www.sota2.com/research/sota/face-anti-spoofing-on-casia-rfs-test>)

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

Data updated: 2026-02-26T05:23:27.143Z

Evaluation of Face Anti-Spoofing performance on the test split of the CASIA-RFS dataset, typically measured using APCER, BPCER, ACER, and Top-1 accuracy.

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 | Face anti-spoofing |
| Dataset (including any stated split) | CASIA-RFS (test) |
| Metric | APCER |
| 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

- [APCER](<https://www.sota2.com/research/sota/face-anti-spoofing-on-casia-rfs-test.md?metric=APCER>): Lower is better; unit: PERCENT.

- [BPCER](<https://www.sota2.com/research/sota/face-anti-spoofing-on-casia-rfs-test.md?metric=BPCER>): Lower is better; unit: PERCENT.

- [ACER](<https://www.sota2.com/research/sota/face-anti-spoofing-on-casia-rfs-test.md?metric=ACER>): Lower is better; unit: PERCENT.

- [Top-1 Acc](<https://www.sota2.com/research/sota/face-anti-spoofing-on-casia-rfs-test.md?metric=Top-1%20Acc>): Higher is better; unit: PERCENT.

## Recorded results

| Method | APCER | Result date | Report paper |
| --- | --- | --- | --- |
| FASNet | 1.23 | Not recorded | 68fa69481e209131cea21254 |
| 3D Virtual Synthesis | 4.68 | Not recorded | 68fa69481e209131cea21254 |
| Patch-based CNN | 12.93 | Not recorded | 68fa69481e209131cea21254 |
| Baseline | 20.96 | Not recorded | 68fa69481e209131cea21254 |

### FASNet

APCER: 1.23. Result ID: 698da1c78b517eb43322c7a1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69481e209131cea21254.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### 3D Virtual Synthesis

APCER: 4.68. Result ID: 698da1c78b517eb43322c7a4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69481e209131cea21254.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69481e209131cea21254.md>)

Recorded evaluation configuration: {"external live data":"MultiPIE","data balancing strategy":"true"}. This record does not assert independent reproduction.

### Patch-based CNN

APCER: 12.93. Result ID: 698da1c78b517eb43322c7a2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69481e209131cea21254.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Baseline

APCER: 20.96. Result ID: 698da1c78b517eb43322c7a3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69481e209131cea21254.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69481e209131cea21254.md>)

Recorded evaluation configuration: {"synthetic data":"None","external live data":"None"}. This record does not assert independent reproduction.

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