# Jailbreak Attack Defense on Mousetrap

Source: [Jailbreak Attack Defense on Mousetrap](<https://www.sota2.com/research/sota/jailbreak-attack-defense-on-mousetrap>)

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

Data updated: 2026-05-07T08:08:34.887Z

Evaluation of model performance defending against jailbreak attacks using the Mousetrap dataset, measured by FFR (Reasoning) and FFR (Final Answer).

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 Defense |
| Dataset (including any stated split) | Mousetrap |
| Metric | FFR (Reasoning) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 17 of 17 |
| 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

- [FFR (Reasoning)](<https://www.sota2.com/research/sota/jailbreak-attack-defense-on-mousetrap.md?metric=FFR%20(Reasoning)>): Higher is better; unit: PERCENT.

- [FFR (Final Answer)](<https://www.sota2.com/research/sota/jailbreak-attack-defense-on-mousetrap.md?metric=FFR%20(Final%20Answer)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | FFR (Reasoning) | Result date | Report paper |
| --- | --- | --- | --- |
| Paraphrase | 22.7 | Not recorded | 68fa7a721e209131cea8346b |
| No Defense | 18.2 | Not recorded | 68fa7a721e209131cea8346b |
| ThinkingI | 11.4 | Not recorded | 68fa7a721e209131cea8346b |
| No Defense | 11.4 | Not recorded | 68fa7a721e209131cea8346b |
| SAFEPATH-ZS | 11.4 | Not recorded | 68fa7a721e209131cea8346b |
| Paraphrase | 9.1 | Not recorded | 68fa7a721e209131cea8346b |
| Self-Reminder | 9.1 | Not recorded | 68fa7a721e209131cea8346b |
| RealSafe-R1 | 7.3 | Not recorded | 68fa7a721e209131cea8346b |
| Self-Reminder | 6.8 | Not recorded | 68fa7a721e209131cea8346b |
| RealSafe-R1 | 5 | Not recorded | 68fa7a721e209131cea8346b |
| SafeKey | 4.5 | Not recorded | 68fa7a721e209131cea8346b |
| SmoothLLM | 2.3 | Not recorded | 68fa7a721e209131cea8346b |
| SAFEPATH-ZS | 2.3 | Not recorded | 68fa7a721e209131cea8346b |
| ReasoningGuard | 2.3 | Not recorded | 68fa7a721e209131cea8346b |
| SmoothLLM | 2.3 | Not recorded | 68fa7a721e209131cea8346b |
| ThinkingI | 2.3 | Not recorded | 68fa7a721e209131cea8346b |
| ReasoningGuard | 0 | Not recorded | 68fa7a721e209131cea8346b |

### Paraphrase

FFR (Reasoning): 22.7. Result ID: 69fc487847f34ce924ded978.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a721e209131cea8346b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa707f1e209131cea4b7c6.md>)

Recorded evaluation configuration: {"Model":"R1-Qwen-32B"}. This record does not assert independent reproduction.

### No Defense

FFR (Reasoning): 18.2. Result ID: 69fc487847f34ce924ded96d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a721e209131cea8346b.md>)

Recorded evaluation configuration: {"Model":"R1-Qwen-14B"}. This record does not assert independent reproduction.

### ThinkingI

FFR (Reasoning): 11.4. Result ID: 69fc487847f34ce924ded973.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a721e209131cea8346b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78b31e209131cea79d3c.md>)

Recorded evaluation configuration: {"Model":"R1-Qwen-14B"}. This record does not assert independent reproduction.

### No Defense

FFR (Reasoning): 11.4. Result ID: 69fc487847f34ce924ded976.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a721e209131cea8346b.md>)

Recorded evaluation configuration: {"Model":"R1-Qwen-32B"}. This record does not assert independent reproduction.

### SAFEPATH-ZS

FFR (Reasoning): 11.4. Result ID: 69fc487847f34ce924ded97c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a721e209131cea8346b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa790c1e209131cea7bde6.md>)

Recorded evaluation configuration: {"Model":"R1-Qwen-32B"}. This record does not assert independent reproduction.

### Paraphrase

FFR (Reasoning): 9.1. Result ID: 69fc487847f34ce924ded970.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a721e209131cea8346b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa707f1e209131cea4b7c6.md>)

Recorded evaluation configuration: {"Model":"R1-Qwen-14B"}. This record does not assert independent reproduction.

### Self-Reminder

FFR (Reasoning): 9.1. Result ID: 69fc487847f34ce924ded971.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a721e209131cea8346b.md>)

Recorded evaluation configuration: {"Model":"R1-Qwen-14B"}. This record does not assert independent reproduction.

### RealSafe-R1

FFR (Reasoning): 7.3. Result ID: 69fc487847f34ce924ded96e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a721e209131cea8346b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa780e1e209131cea76907.md>)

Recorded evaluation configuration: {"Model":"R1-Qwen-14B"}. This record does not assert independent reproduction.

### Self-Reminder

FFR (Reasoning): 6.8. Result ID: 69fc487847f34ce924ded979.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a721e209131cea8346b.md>)

Recorded evaluation configuration: {"Model":"R1-Qwen-32B"}. This record does not assert independent reproduction.

### RealSafe-R1

FFR (Reasoning): 5. Result ID: 69fc487847f34ce924ded977.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a721e209131cea8346b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa780e1e209131cea76907.md>)

Recorded evaluation configuration: {"Model":"R1-Qwen-32B"}. This record does not assert independent reproduction.

### SafeKey

FFR (Reasoning): 4.5. Result ID: 69fc487847f34ce924ded96f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a721e209131cea8346b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78be1e209131cea7a311.md>)

Recorded evaluation configuration: {"Model":"R1-Qwen-14B"}. This record does not assert independent reproduction.

### SmoothLLM

FFR (Reasoning): 2.3. Result ID: 69fc487847f34ce924ded972.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a721e209131cea8346b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73961e209131cea5d658.md>)

Recorded evaluation configuration: {"Model":"R1-Qwen-14B"}. This record does not assert independent reproduction.

### SAFEPATH-ZS

FFR (Reasoning): 2.3. Result ID: 69fc487847f34ce924ded974.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a721e209131cea8346b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa790c1e209131cea7bde6.md>)

Recorded evaluation configuration: {"Model":"R1-Qwen-14B"}. This record does not assert independent reproduction.

### ReasoningGuard

FFR (Reasoning): 2.3. Result ID: 69fc487847f34ce924ded975.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a721e209131cea8346b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a721e209131cea8346b.md>)

Recorded evaluation configuration: {"Model":"R1-Qwen-14B"}. This record does not assert independent reproduction.

### SmoothLLM

FFR (Reasoning): 2.3. Result ID: 69fc487847f34ce924ded97a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a721e209131cea8346b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73961e209131cea5d658.md>)

Recorded evaluation configuration: {"Model":"R1-Qwen-32B"}. This record does not assert independent reproduction.

### ThinkingI

FFR (Reasoning): 2.3. Result ID: 69fc487847f34ce924ded97b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a721e209131cea8346b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78b31e209131cea79d3c.md>)

Recorded evaluation configuration: {"Model":"R1-Qwen-32B"}. This record does not assert independent reproduction.

### ReasoningGuard

FFR (Reasoning): 0. Result ID: 69fc487847f34ce924ded97d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a721e209131cea8346b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a721e209131cea8346b.md>)

Recorded evaluation configuration: {"Model":"R1-Qwen-32B"}. This record does not assert independent reproduction.

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