# Trojaned Model Detection on CIFAR10 Densenet121 (test)

Source: [Trojaned Model Detection on CIFAR10 Densenet121 (test)](<https://www.sota2.com/research/sota/trojaned-model-detection-on-cifar10-densenet121-test>)

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

Data updated: 2026-02-26T05:27:55.581Z

Evaluation of a model's capability to detect Trojan attacks on a Densenet121 model using the CIFAR-10 test split, measured by Accuracy (ACC) and Area Under the Curve (AUC).

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 | Trojaned Model Detection |
| Dataset (including any stated split) | CIFAR10 Densenet121 (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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/trojaned-model-detection-on-cifar10-densenet121-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [AUC](<https://www.sota2.com/research/sota/trojaned-model-detection-on-cifar10-densenet121-test.md?metric=AUC>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Topo | 84 | Not recorded | 68fa6a211e209131cea2628f |
| DFTND | 59 | Not recorded | 68fa6a211e209131cea2628f |
| Corr | 58 | Not recorded | 68fa6a211e209131cea2628f |
| ULP | 55 | Not recorded | 68fa6a211e209131cea2628f |
| NC | 47 | Not recorded | 68fa6a211e209131cea2628f |

### Topo

Accuracy: 84. Result ID: 698e1237ffc3901de09a9241.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a211e209131cea2628f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a211e209131cea2628f.md>)

Recorded evaluation configuration: {"architecture":"Densenet121"}. This record does not assert independent reproduction.

### DFTND

Accuracy: 59. Result ID: 698e1237ffc3901de09a923e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a211e209131cea2628f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680b1e209131cea19c39.md>)

Recorded evaluation configuration: {"architecture":"Densenet121"}. This record does not assert independent reproduction.

### Corr

Accuracy: 58. Result ID: 698e1237ffc3901de09a9240.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a211e209131cea2628f.md>)

Recorded evaluation configuration: {"architecture":"Densenet121"}. This record does not assert independent reproduction.

### ULP

Accuracy: 55. Result ID: 698e1237ffc3901de09a923f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a211e209131cea2628f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67881e209131cea16b47.md>)

Recorded evaluation configuration: {"architecture":"Densenet121"}. This record does not assert independent reproduction.

### NC

Accuracy: 47. Result ID: 698e1237ffc3901de09a923d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a211e209131cea2628f.md>)

Recorded evaluation configuration: {"architecture":"Densenet121"}. This record does not assert independent reproduction.

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