# Jailbreak Attack on AdversarialBenchmark Source: [Jailbreak Attack on AdversarialBenchmark]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:24:03.878Z Evaluation of model performance against jailbreak attacks using the AdversarialBenchmark dataset, measuring various components of 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) | AdversarialBenchmark | | Metric | ASR (m) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 15 of 15 | | 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 - [ASR (m)](): Higher is better; unit: PERCENT. - [ASR](): Higher is better; unit: PERCENT. ## Recorded results | Method | ASR (m) | Result date | Report paper | | --- | --- | --- | --- | | S-PIEL | 0.512 | Not recorded | 68fa7c001e209131cea8bd0d | | S-PIEL | 0.498 | Not recorded | 68fa7c001e209131cea8bd0d | | S-PIEL | 0.498 | Not recorded | 68fa7c001e209131cea8bd0d | | S-PIEL | 0.38 | Not recorded | 68fa7c001e209131cea8bd0d | | S-PIEL | 0.354 | Not recorded | 68fa7c001e209131cea8bd0d | | GCG | 0.194 | Not recorded | 68fa7c001e209131cea8bd0d | | GCG | 0.146 | Not recorded | 68fa7c001e209131cea8bd0d | | GCG | 0.12 | Not recorded | 68fa7c001e209131cea8bd0d | | GCG | 0.056 | Not recorded | 68fa7c001e209131cea8bd0d | | Vanilla Prompt | 0 | Not recorded | 68fa7c001e209131cea8bd0d | | Vanilla Prompt | 0 | Not recorded | 68fa7c001e209131cea8bd0d | | Vanilla Prompt | 0 | Not recorded | 68fa7c001e209131cea8bd0d | | Vanilla Prompt | 0 | Not recorded | 68fa7c001e209131cea8bd0d | | Vanilla Prompt | 0 | Not recorded | 68fa7c001e209131cea8bd0d | | GCG | 0 | Not recorded | 68fa7c001e209131cea8bd0d | ### S-PIEL ASR (m): 0.512. Result ID: 698b8dee7a967eddb76f89df. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model Type":"Mistral 7B"}. This record does not assert independent reproduction. ### S-PIEL ASR (m): 0.498. Result ID: 698b8dee7a967eddb76f89d9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model Type":"Llama-2-7B"}. This record does not assert independent reproduction. ### S-PIEL ASR (m): 0.498. Result ID: 698b8dee7a967eddb76f89e2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model Type":"Gemma-2-9B"}. This record does not assert independent reproduction. ### S-PIEL ASR (m): 0.38. Result ID: 698b8dee7a967eddb76f89dc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model Type":"Llama-3.1-8B"}. This record does not assert independent reproduction. ### S-PIEL ASR (m): 0.354. Result ID: 698b8dee7a967eddb76f89e5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model Type":"Llama-3.1-8B (DeepSeek-R1-Distilled)"}. This record does not assert independent reproduction. ### GCG ASR (m): 0.194. Result ID: 698b8dee7a967eddb76f89de. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model Type":"Mistral 7B"}. This record does not assert independent reproduction. ### GCG ASR (m): 0.146. Result ID: 698b8dee7a967eddb76f89e1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model Type":"Gemma-2-9B"}. This record does not assert independent reproduction. ### GCG ASR (m): 0.12. Result ID: 698b8dee7a967eddb76f89d8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model Type":"Llama-2-7B"}. This record does not assert independent reproduction. ### GCG ASR (m): 0.056. Result ID: 698b8dee7a967eddb76f89db. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model Type":"Llama-3.1-8B"}. This record does not assert independent reproduction. ### Vanilla Prompt ASR (m): 0. Result ID: 698b8dee7a967eddb76f89d7. [Reporting paper]() Recorded evaluation configuration: {"Target Model Type":"Llama-2-7B"}. This record does not assert independent reproduction. ### Vanilla Prompt ASR (m): 0. Result ID: 698b8dee7a967eddb76f89da. [Reporting paper]() Recorded evaluation configuration: {"Target Model Type":"Llama-3.1-8B"}. This record does not assert independent reproduction. ### Vanilla Prompt ASR (m): 0. Result ID: 698b8dee7a967eddb76f89dd. [Reporting paper]() Recorded evaluation configuration: {"Target Model Type":"Mistral 7B"}. This record does not assert independent reproduction. ### Vanilla Prompt ASR (m): 0. Result ID: 698b8dee7a967eddb76f89e0. [Reporting paper]() Recorded evaluation configuration: {"Target Model Type":"Gemma-2-9B"}. This record does not assert independent reproduction. ### Vanilla Prompt ASR (m): 0. Result ID: 698b8dee7a967eddb76f89e3. [Reporting paper]() Recorded evaluation configuration: {"Target Model Type":"Llama-3.1-8B (DeepSeek-R1-Distilled)"}. This record does not assert independent reproduction. ### GCG ASR (m): 0. Result ID: 698b8dee7a967eddb76f89e4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model Type":"Llama-3.1-8B (DeepSeek-R1-Distilled)"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.