# Safety Alignment on RAB Violence (adversarial prompts) Source: [Safety Alignment on RAB Violence (adversarial prompts)]() Collection index: [llms.txt]() Data updated: 2026-07-08T07:36:20.350Z Evaluation of model safety alignment performance specifically against adversarial prompts related to violence, measured by 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 | Safety Alignment | | Dataset (including any stated split) | RAB Violence (adversarial prompts) | | Metric | ASR | | Unit | PERCENT | | Direction | Lower is better | | Results loaded | 16 of 16 | | 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](): Lower is better; unit: PERCENT. ## Recorded results | Method | ASR | Result date | Report paper | | --- | --- | --- | --- | | AEGIS | 1 | Not recorded | 6a4dd9904da6617fe9198b3d | | AEGIS | 3 | Not recorded | 6a4dd9904da6617fe9198b3d | | SafeClip | 4 | Not recorded | 6a4dd9904da6617fe9198b3d | | SLD-Strong | 7 | Not recorded | 6a4dd9904da6617fe9198b3d | | SAFREE | 8 | Not recorded | 6a4dd9904da6617fe9198b3d | | CAD | 8 | Not recorded | 6a4dd9904da6617fe9198b3d | | SafeGuider | 10 | Not recorded | 6a4dd9904da6617fe9198b3d | | UCE | 11 | Not recorded | 6a4dd9904da6617fe9198b3d | | SDID | 11 | Not recorded | 6a4dd9904da6617fe9198b3d | | Receler | 15 | Not recorded | 6a4dd9904da6617fe9198b3d | | SD 2.1 | 22 | Not recorded | 6a4dd9904da6617fe9198b3d | | SLD-Medium | 23 | Not recorded | 6a4dd9904da6617fe9198b3d | | ESD-u | 24 | Not recorded | 6a4dd9904da6617fe9198b3d | | Diff-QuickFix | 25 | Not recorded | 6a4dd9904da6617fe9198b3d | | SLD-Weak | 39 | Not recorded | 6a4dd9904da6617fe9198b3d | | SD 1.4 | 49 | Not recorded | 6a4dd9904da6617fe9198b3d | ### AEGIS ASR: 1. Result ID: 6a4dfde460b88bb339d7419d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"AEGIS (Ours)","Base Model":"SD 2.1"}. This record does not assert independent reproduction. ### AEGIS ASR: 3. Result ID: 6a4dfde460b88bb339d7419c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"AEGIS (Ours)","Base Model":"SD 1.4"}. This record does not assert independent reproduction. ### SafeClip ASR: 4. Result ID: 6a4dfde460b88bb339d74190. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Input-Space"}. This record does not assert independent reproduction. ### SLD-Strong ASR: 7. Result ID: 6a4dfde460b88bb339d74199. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"Trigger-Specific"}. This record does not assert independent reproduction. ### SAFREE ASR: 8. Result ID: 6a4dfde460b88bb339d74191. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Input-Space"}. This record does not assert independent reproduction. ### CAD ASR: 8. Result ID: 6a4dfde460b88bb339d7419b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Feature Pruning"}. This record does not assert independent reproduction. ### SafeGuider ASR: 10. Result ID: 6a4dfde460b88bb339d74192. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Input-Space"}. This record does not assert independent reproduction. ### UCE ASR: 11. Result ID: 6a4dfde460b88bb339d74194. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Trigger-Specific"}. This record does not assert independent reproduction. ### SDID ASR: 11. Result ID: 6a4dfde460b88bb339d7419a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"Trigger-Specific"}. This record does not assert independent reproduction. ### Receler ASR: 15. Result ID: 6a4dfde460b88bb339d74195. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Trigger-Specific"}. This record does not assert independent reproduction. ### SD 2.1 ASR: 22. Result ID: 6a4dfde460b88bb339d7418f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"No Alignment"}. This record does not assert independent reproduction. ### SLD-Medium ASR: 23. Result ID: 6a4dfde460b88bb339d74198. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"Trigger-Specific"}. This record does not assert independent reproduction. ### ESD-u ASR: 24. Result ID: 6a4dfde460b88bb339d74193. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Trigger-Specific"}. This record does not assert independent reproduction. ### Diff-QuickFix ASR: 25. Result ID: 6a4dfde460b88bb339d74196. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Trigger-Specific"}. This record does not assert independent reproduction. ### SLD-Weak ASR: 39. Result ID: 6a4dfde460b88bb339d74197. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"Trigger-Specific"}. This record does not assert independent reproduction. ### SD 1.4 ASR: 49. Result ID: 6a4dfde460b88bb339d7418e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"No Alignment"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.