# Jailbreak Attack on AdvBench (WASR, W-Toxicity Score) Source: [Jailbreak Attack on AdvBench (WASR, W-Toxicity Score)]() Collection index: [llms.txt]() Data updated: 2026-05-19T09:31:56.701Z Evaluation of model susceptibility to jailbreak attacks using the AdvBench dataset, reporting WASR (Weighted Attack Success Rate) and W-Toxicity 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 | Jailbreak Attack | | Dataset (including any stated split) | AdvBench | | Metric | WASR | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 - [WASR](): Higher is better; unit: PERCENT. - [W-Toxicity Score](): Lower is better; unit: PERCENT. ## Recorded results | Method | WASR | Result date | Report paper | | --- | --- | --- | --- | | wide-net-casting jailbreak method | 100 | Not recorded | 6a0beec1dbc836b87d82c63a | | Naive Strategy 2 | 95.8 | Not recorded | 6a0beec1dbc836b87d82c63a | | Naive Strategy 1 | 95.1 | Not recorded | 6a0beec1dbc836b87d82c63a | | Baseline (ReMiss) | 92.3 | Not recorded | 6a0beec1dbc836b87d82c63a | | wide-net-casting jailbreak method | 76.7 | Not recorded | 6a0beec1dbc836b87d82c63a | | wide-net-casting jailbreak method | 72.8 | Not recorded | 6a0beec1dbc836b87d82c63a | | Naive Strategy 2 | 64.9 | Not recorded | 6a0beec1dbc836b87d82c63a | | Naive Strategy 1 | 64.1 | Not recorded | 6a0beec1dbc836b87d82c63a | | Baseline (ReMiss) | 61.5 | Not recorded | 6a0beec1dbc836b87d82c63a | | Naive Strategy 2 | 60.3 | Not recorded | 6a0beec1dbc836b87d82c63a | | Naive Strategy 1 | 59.2 | Not recorded | 6a0beec1dbc836b87d82c63a | | Baseline (ReMiss) | 56.1 | Not recorded | 6a0beec1dbc836b87d82c63a | ### wide-net-casting jailbreak method WASR: 100. Result ID: 6a0c2d63fbc373592c02959c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Safety Alignment Setting":"Original Safety Alignment"}. This record does not assert independent reproduction. ### Naive Strategy 2 WASR: 95.8. Result ID: 6a0c2d63fbc373592c029599. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Safety Alignment Setting":"Original Safety Alignment"}. This record does not assert independent reproduction. ### Naive Strategy 1 WASR: 95.1. Result ID: 6a0c2d63fbc373592c029596. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Safety Alignment Setting":"Original Safety Alignment"}. This record does not assert independent reproduction. ### Baseline (ReMiss) WASR: 92.3. Result ID: 6a0c2d63fbc373592c029593. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Safety Alignment Setting":"Original Safety Alignment"}. This record does not assert independent reproduction. ### wide-net-casting jailbreak method WASR: 76.7. Result ID: 6a0c2d63fbc373592c02959d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Safety Alignment Setting":"Original Safety Alignment + SmoothLLM"}. This record does not assert independent reproduction. ### wide-net-casting jailbreak method WASR: 72.8. Result ID: 6a0c2d63fbc373592c02959e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Safety Alignment Setting":"Original Safety Alignment + RobustKV"}. This record does not assert independent reproduction. ### Naive Strategy 2 WASR: 64.9. Result ID: 6a0c2d63fbc373592c02959a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Safety Alignment Setting":"Original Safety Alignment + SmoothLLM"}. This record does not assert independent reproduction. ### Naive Strategy 1 WASR: 64.1. Result ID: 6a0c2d63fbc373592c029597. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Safety Alignment Setting":"Original Safety Alignment + SmoothLLM"}. This record does not assert independent reproduction. ### Baseline (ReMiss) WASR: 61.5. Result ID: 6a0c2d63fbc373592c029594. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Safety Alignment Setting":"Original Safety Alignment + SmoothLLM"}. This record does not assert independent reproduction. ### Naive Strategy 2 WASR: 60.3. Result ID: 6a0c2d63fbc373592c02959b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Safety Alignment Setting":"Original Safety Alignment + RobustKV"}. This record does not assert independent reproduction. ### Naive Strategy 1 WASR: 59.2. Result ID: 6a0c2d63fbc373592c029598. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Safety Alignment Setting":"Original Safety Alignment + RobustKV"}. This record does not assert independent reproduction. ### Baseline (ReMiss) WASR: 56.1. Result ID: 6a0c2d63fbc373592c029595. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Safety Alignment Setting":"Original Safety Alignment + RobustKV"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.