# Adversarial Attack Detection on Adaptive Threshold Evasion

Source: [Adversarial Attack Detection on Adaptive Threshold Evasion](<https://www.sota2.com/research/sota/adversarial-attack-detection-on-adaptive-threshold-evasion>)

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

Data updated: 2026-03-16T08:49:03.989Z

Evaluation of a model's ability to detect adversarial attacks specifically targeting the Adaptive Threshold Evasion scenario, reporting standard detection metrics like Precision, Recall, and F1 score.

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 | Adversarial Attack Detection |
| Dataset (including any stated split) | Adaptive Threshold Evasion |
| Metric | Precision |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [Precision](<https://www.sota2.com/research/sota/adversarial-attack-detection-on-adaptive-threshold-evasion.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/adversarial-attack-detection-on-adaptive-threshold-evasion.md?metric=Recall>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/adversarial-attack-detection-on-adaptive-threshold-evasion.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [AUC](<https://www.sota2.com/research/sota/adversarial-attack-detection-on-adaptive-threshold-evasion.md?metric=AUC>): Higher is better; unit: PERCENT.

- [FPR](<https://www.sota2.com/research/sota/adversarial-attack-detection-on-adaptive-threshold-evasion.md?metric=FPR>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Precision | Result date | Report paper |
| --- | --- | --- | --- |
| SpectralGuard (Multi-Layer) | 94.1 | Not recorded | 69b78e970636e5bf4afbdc5f |
| SpectralGuard (Single-Layer) | 48.4 | Not recorded | 69b78e970636e5bf4afbdc5f |

### SpectralGuard (Multi-Layer)

Precision: 94.1. Result ID: 69b7c30247f34ce9249f7823.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e970636e5bf4afbdc5f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b78e970636e5bf4afbdc5f.md>)

Recorded evaluation configuration: {"Setting":"Adaptive","Attacker":"Threshold evasion","Latency":"\< 15ms/tok","N":"100","Model":"Mamba-130M"}. This record does not assert independent reproduction.

### SpectralGuard (Single-Layer)

Precision: 48.4. Result ID: 69b7c30247f34ce9249f7822.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e970636e5bf4afbdc5f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b78e970636e5bf4afbdc5f.md>)

Recorded evaluation configuration: {"Setting":"Adaptive","Attacker":"Threshold evasion","Latency":"\< 5ms/tok","N":"500","Model":"Mamba-130M"}. This record does not assert independent reproduction.

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