# Safety Evaluation (Attack Success Rate) on Kling Source: [Safety Evaluation (Attack Success Rate) on Kling]() Collection index: [llms.txt]() Data updated: 2026-03-10T08:31:00.074Z Evaluation of model safety performance across various harmful content categories (e.g., Pornography, Violence, Discrimination, Illegal Activities) using the Kling dataset, 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 Evaluation (Attack Success Rate) | | Dataset (including any stated split) | Kling | | Metric | ASR (Pornography) | | Unit | PERCENT | | Direction | Lower is better | | Results loaded | 5 of 5 | | 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 (Pornography)](): Lower is better; unit: PERCENT. - [ASR (Borderline Pornography)](): Lower is better; unit: PERCENT. - [ASR (Violence)](): Lower is better; unit: PERCENT. - [ASR (Gore)](): Lower is better; unit: PERCENT. - [ASR (Disturbing Content)](): Lower is better; unit: PERCENT. - [ASR (Public Figures)](): Lower is better; unit: PERCENT. - [ASR (Discrimination)](): Lower is better; unit: PERCENT. - [ASR (Political Sensitivity)](): Lower is better; unit: PERCENT. - [ASR (Copyright)](): Lower is better; unit: PERCENT. - [ASR (Illegal Activities)](): Lower is better; unit: PERCENT. - [ASR (Misinformation)](): Lower is better; unit: PERCENT. - [ASR (Sequential Action)](): Lower is better; unit: PERCENT. - [ASR (Dynamic Variation)](): Lower is better; unit: PERCENT. - [ASR (Coherent Contextual)](): Lower is better; unit: PERCENT. - [Average ASR](): Lower is better; unit: PERCENT. ## Recorded results | Method | ASR (Pornography) | Result date | Report paper | | --- | --- | --- | --- | | TSB | 22 | Not recorded | 69afa5662d603e6de3e43878 | | DACA | 34 | Not recorded | 69afa5662d603e6de3e43878 | | RAB | 42 | Not recorded | 69afa5662d603e6de3e43878 | | VEIL | 88 | Not recorded | 69afa5662d603e6de3e43878 | | TFM | 94 | Not recorded | 69afa5662d603e6de3e43878 | ### TSB ASR (Pornography): 22. Result ID: 69afd6c06dbb7075b9583014. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DACA ASR (Pornography): 34. Result ID: 69afd6c06dbb7075b9583016. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### RAB ASR (Pornography): 42. Result ID: 69afd6c06dbb7075b9583015. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### VEIL ASR (Pornography): 88. Result ID: 69afd6c06dbb7075b9583017. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### TFM ASR (Pornography): 94. Result ID: 69afd6c06dbb7075b9583018. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.