# Spam Detection on Twitter Spam Detection 1000 spammers (test)

Source: [Spam Detection on Twitter Spam Detection 1000 spammers (test)](<https://www.sota2.com/research/sota/spam-detection-on-twitter-spam-detection-1000-spammers-test>)

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

Data updated: 2026-02-26T05:51:36.589Z

Evaluation of Spam Detection performance on the specific '1000 spammers' test split of the Twitter dataset, reporting Margin and Certification Success metrics.

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 | Spam Detection |
| Dataset (including any stated split) | Twitter Spam Detection 1000 spammers (test) |
| Metric | Margin |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 10 of 10 |
| 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

- [Margin](<https://www.sota2.com/research/sota/spam-detection-on-twitter-spam-detection-1000-spammers-test.md?metric=Margin>): Higher is better; unit: SCALAR.

- [Certification Success](<https://www.sota2.com/research/sota/spam-detection-on-twitter-spam-detection-1000-spammers-test.md?metric=Certification%20Success>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Margin | Result date | Report paper |
| --- | --- | --- | --- |
| NU-δ-MDt | 2.41 | Not recorded | 68fa6b2c1e209131cea2c8a7 |
| NU-δ-MDt | 2.41 | Not recorded | 68fa6b2c1e209131cea2c8a7 |
| Uniform-δ | 2.4 | Not recorded | 68fa6b2c1e209131cea2c8a7 |
| Uniform-δ | 2.4 | Not recorded | 68fa6b2c1e209131cea2c8a7 |
| NU-δ-MDt | 2.06 | Not recorded | 68fa6b2c1e209131cea2c8a7 |
| Uniform-δ | 2.04 | Not recorded | 68fa6b2c1e209131cea2c8a7 |
| NU-δ-MDt | 1.9 | Not recorded | 68fa6b2c1e209131cea2c8a7 |
| Uniform-δ | 1.84 | Not recorded | 68fa6b2c1e209131cea2c8a7 |
| NU-δ-MDt | 1.11 | Not recorded | 68fa6b2c1e209131cea2c8a7 |
| Uniform-δ | 1.07 | Not recorded | 68fa6b2c1e209131cea2c8a7 |

### NU-δ-MDt

Margin: 2.41. Result ID: 698e65ecffc3901de09d4109.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b2c1e209131cea2c8a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b2c1e209131cea2c8a7.md>)

[Implementation](<https://github.com/amazon-research/adversarial-robustness-with-nonuniform-perturbations>)

Recorded evaluation configuration: {"Defense S.R.":"63.4 ± 0.74%","Cert. Method":"NU-Cert-MD"}. This record does not assert independent reproduction.

### NU-δ-MDt

Margin: 2.41. Result ID: 698e65ecffc3901de09d410a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b2c1e209131cea2c8a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b2c1e209131cea2c8a7.md>)

[Implementation](<https://github.com/amazon-research/adversarial-robustness-with-nonuniform-perturbations>)

Recorded evaluation configuration: {"Defense S.R.":"63.4 ± 0.74%","Cert. Method":"NU-Cert-MDt"}. This record does not assert independent reproduction.

### Uniform-δ

Margin: 2.4. Result ID: 698e65ecffc3901de09d4104.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b2c1e209131cea2c8a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b2c1e209131cea2c8a7.md>)

[Implementation](<https://github.com/amazon-research/adversarial-robustness-with-nonuniform-perturbations>)

Recorded evaluation configuration: {"Defense S.R.":"54.87 ± 1.1%","Cert. Method":"NU-Cert-MD"}. This record does not assert independent reproduction.

### Uniform-δ

Margin: 2.4. Result ID: 698e65ecffc3901de09d4105.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b2c1e209131cea2c8a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b2c1e209131cea2c8a7.md>)

[Implementation](<https://github.com/amazon-research/adversarial-robustness-with-nonuniform-perturbations>)

Recorded evaluation configuration: {"Defense S.R.":"54.87 ± 1.1%","Cert. Method":"NU-Cert-MDt"}. This record does not assert independent reproduction.

### NU-δ-MDt

Margin: 2.06. Result ID: 698e65ecffc3901de09d4108.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b2c1e209131cea2c8a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b2c1e209131cea2c8a7.md>)

[Implementation](<https://github.com/amazon-research/adversarial-robustness-with-nonuniform-perturbations>)

Recorded evaluation configuration: {"Defense S.R.":"63.4 ± 0.74%","Cert. Method":"NU-Cert-Pearson"}. This record does not assert independent reproduction.

### Uniform-δ

Margin: 2.04. Result ID: 698e65ecffc3901de09d4103.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b2c1e209131cea2c8a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b2c1e209131cea2c8a7.md>)

[Implementation](<https://github.com/amazon-research/adversarial-robustness-with-nonuniform-perturbations>)

Recorded evaluation configuration: {"Defense S.R.":"54.87 ± 1.1%","Cert. Method":"NU-Cert-Pearson"}. This record does not assert independent reproduction.

### NU-δ-MDt

Margin: 1.9. Result ID: 698e65ecffc3901de09d4107.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b2c1e209131cea2c8a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b2c1e209131cea2c8a7.md>)

[Implementation](<https://github.com/amazon-research/adversarial-robustness-with-nonuniform-perturbations>)

Recorded evaluation configuration: {"Defense S.R.":"63.4 ± 0.74%","Cert. Method":"NU-Cert-SHAP"}. This record does not assert independent reproduction.

### Uniform-δ

Margin: 1.84. Result ID: 698e65ecffc3901de09d4102.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b2c1e209131cea2c8a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b2c1e209131cea2c8a7.md>)

[Implementation](<https://github.com/amazon-research/adversarial-robustness-with-nonuniform-perturbations>)

Recorded evaluation configuration: {"Defense S.R.":"54.87 ± 1.1%","Cert. Method":"NU-Cert-SHAP"}. This record does not assert independent reproduction.

### NU-δ-MDt

Margin: 1.11. Result ID: 698e65ecffc3901de09d4106.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b2c1e209131cea2c8a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b2c1e209131cea2c8a7.md>)

[Implementation](<https://github.com/amazon-research/adversarial-robustness-with-nonuniform-perturbations>)

Recorded evaluation configuration: {"Defense S.R.":"63.4 ± 0.74%","Cert. Method":"Uniform-Cert"}. This record does not assert independent reproduction.

### Uniform-δ

Margin: 1.07. Result ID: 698e65ecffc3901de09d4101.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b2c1e209131cea2c8a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b2c1e209131cea2c8a7.md>)

[Implementation](<https://github.com/amazon-research/adversarial-robustness-with-nonuniform-perturbations>)

Recorded evaluation configuration: {"Defense S.R.":"54.87 ± 1.1%","Cert. Method":"Uniform-Cert"}. This record does not assert independent reproduction.

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