# Jailbreak Attack on AdvBench (ASR)

Source: [Jailbreak Attack on AdvBench (ASR)](<https://www.sota2.com/research/sota/jailbreak-attack-on-advbench-asr>)

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

Data updated: 2026-07-03T07:26:49.815Z

Evaluation of model susceptibility to jailbreak attacks using the AdvBench dataset, reporting only the Attack Success Rate (ASR).

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 | Jailbreak Attack |
| Dataset (including any stated split) | AdvBench |
| Metric | Attack Success Rate (ASR) |
| 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

- [Attack Success Rate (ASR)](<https://www.sota2.com/research/sota/jailbreak-attack-on-advbench-asr.md?metric=Attack%20Success%20Rate%20(ASR)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Attack Success Rate (ASR) | Result date | Report paper |
| --- | --- | --- | --- |
| STEER | 32 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| GCG | 26.9 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| CSRT | 14.7 | Not recorded | 6a47420e143ebdcacacc5ce8 |

### STEER

Attack Success Rate (ASR): 32. Result ID: 6a47643860b88bb33992cc78.

[Reporting paper](<https://www.sota2.com/research/paper/6a47420e143ebdcacacc5ce8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a47420e143ebdcacacc5ce8.md>)

Recorded evaluation configuration: {"Target Model":"GPT-4o-mini"}. This record does not assert independent reproduction.

### GCG

Attack Success Rate (ASR): 26.9. Result ID: 6a47643860b88bb33992cc79.

[Reporting paper](<https://www.sota2.com/research/paper/6a47420e143ebdcacacc5ce8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71861e209131cea51c3b.md>)

Recorded evaluation configuration: {"Target Model":"GPT-4o-mini"}. This record does not assert independent reproduction.

### CSRT

Attack Success Rate (ASR): 14.7. Result ID: 6a47643860b88bb33992cc7a.

[Reporting paper](<https://www.sota2.com/research/paper/6a47420e143ebdcacacc5ce8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d43f.md>)

Recorded evaluation configuration: {"Target Model":"GPT-4o-mini"}. This record does not assert independent reproduction.

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