# Active GIA Detection on CIFAR-10 Cross-Silo (10 clients)

Source: [Active GIA Detection on CIFAR-10 Cross-Silo (10 clients)](<https://www.sota2.com/research/sota/active-gia-detection-on-cifar-10-cross-silo-10-clients>)

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

Data updated: 2026-05-26T10:31:02.594Z

Evaluation of Active GIA (General Integrity Attack) detection performance on a CIFAR-10 dataset distributed across 10 clients in a cross-silo federated learning environment, measured using True Positive Rate and False Positive Rate.

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 | Active GIA Detection |
| Dataset (including any stated split) | CIFAR-10 Cross-Silo, 10 clients |
| Metric | Average True Positive Rate |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [Average True Positive Rate](<https://www.sota2.com/research/sota/active-gia-detection-on-cifar-10-cross-silo-10-clients.md?metric=Average%20True%20Positive%20Rate>): Higher is better; unit: PERCENT.

- [Average False Positive Rate](<https://www.sota2.com/research/sota/active-gia-detection-on-cifar-10-cross-silo-10-clients.md?metric=Average%20False%20Positive%20Rate>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Average True Positive Rate | Result date | Report paper |
| --- | --- | --- | --- |
| lightweight client-side detection techniques | 100 | Not recorded | 6916b77c0052cac1dc65df8b |
| lightweight client-side detection techniques | 100 | Not recorded | 6916b77c0052cac1dc65df8b |
| lightweight client-side detection techniques | 100 | Not recorded | 6916b77c0052cac1dc65df8b |

### lightweight client-side detection techniques

Average True Positive Rate: 100. Result ID: 6a157665fbc373592c0d89ac.

[Reporting paper](<https://www.sota2.com/research/paper/6916b77c0052cac1dc65df8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6916b77c0052cac1dc65df8b.md>)

Recorded evaluation configuration: {"Category":"Handcrafted GIAs","Attack":"\[14\]","Global Model":"ResNet18 \[24\]","Total Rounds":"200","Victim Batch Size":"64","Number of Runs":"10"}. This record does not assert independent reproduction.

### lightweight client-side detection techniques

Average True Positive Rate: 100. Result ID: 6a157665fbc373592c0d89ad.

[Reporting paper](<https://www.sota2.com/research/paper/6916b77c0052cac1dc65df8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6916b77c0052cac1dc65df8b.md>)

Recorded evaluation configuration: {"Category":"Learned GIAs","Attack":"\[6\]","Global Model":"ResNet18 \[24\]","Total Rounds":"200","Victim Batch Size":"64","Number of Runs":"10"}. This record does not assert independent reproduction.

### lightweight client-side detection techniques

Average True Positive Rate: 100. Result ID: 6a157665fbc373592c0d89ae.

[Reporting paper](<https://www.sota2.com/research/paper/6916b77c0052cac1dc65df8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6916b77c0052cac1dc65df8b.md>)

Recorded evaluation configuration: {"Category":"Learned GIAs","Attack":"\[15\]","Global Model":"ResNet34 \[24\]","Total Rounds":"200","Victim Batch Size":"64","Number of Runs":"10"}. This record does not assert independent reproduction.

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