# Refusal Rate Evaluation on CelebA Source: [Refusal Rate Evaluation on CelebA]() Collection index: [llms.txt]() Data updated: 2026-04-13T08:39:55.363Z Evaluation of model refusal behavior on the CelebA dataset, focusing on the Refusal Rate metric. 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 | Refusal Rate Evaluation | | Dataset (including any stated split) | CelebA | | Metric | Refusal Rate | | Unit | PERCENT | | Direction | Lower is better | | Results loaded | 30 of 30 | | 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 - [Refusal Rate](): Lower is better; unit: PERCENT. ## Recorded results | Method | Refusal Rate | Result date | Report paper | | --- | --- | --- | --- | | ImageProtector | 81 | Not recorded | 69dc78627d0172140ec7891f | | ImageProtector | 85 | Not recorded | 69dc78627d0172140ec7891f | | ImageProtector | 86 | Not recorded | 69dc78627d0172140ec7891f | | ImageProtector | 87 | Not recorded | 69dc78627d0172140ec7891f | | ImageProtector | 87 | Not recorded | 69dc78627d0172140ec7891f | | ImageProtector | 87 | Not recorded | 69dc78627d0172140ec7891f | | ImageProtector | 87 | Not recorded | 69dc78627d0172140ec7891f | | ImageProtector | 89 | Not recorded | 69dc78627d0172140ec7891f | | ImageProtector | 90 | Not recorded | 69dc78627d0172140ec7891f | | ImageProtector | 93 | Not recorded | 69dc78627d0172140ec7891f | | ImageProtector | 94 | Not recorded | 69dc78627d0172140ec7891f | | ImageProtector | 94 | Not recorded | 69dc78627d0172140ec7891f | | ImageProtector | 94 | Not recorded | 69dc78627d0172140ec7891f | | ImageProtector | 95 | Not recorded | 69dc78627d0172140ec7891f | | ImageProtector | 95 | Not recorded | 69dc78627d0172140ec7891f | | ImageProtector | 96 | Not recorded | 69dc78627d0172140ec7891f | | ImageProtector | 96 | Not recorded | 69dc78627d0172140ec7891f | | ImageProtector | 97 | Not recorded | 69dc78627d0172140ec7891f | | ImageProtector | 97 | Not recorded | 69dc78627d0172140ec7891f | | ImageProtector | 98 | Not recorded | 69dc78627d0172140ec7891f | | ImageProtector | 98 | Not recorded | 69dc78627d0172140ec7891f | | ImageProtector | 98 | Not recorded | 69dc78627d0172140ec7891f | | ImageProtector | 99 | Not recorded | 69dc78627d0172140ec7891f | | ImageProtector | 99 | Not recorded | 69dc78627d0172140ec7891f | | ImageProtector | 100 | Not recorded | 69dc78627d0172140ec7891f | | ImageProtector | 100 | Not recorded | 69dc78627d0172140ec7891f | | ImageProtector | 100 | Not recorded | 69dc78627d0172140ec7891f | | ImageProtector | 100 | Not recorded | 69dc78627d0172140ec7891f | | ImageProtector | 100 | Not recorded | 69dc78627d0172140ec7891f | | ImageProtector | 100 | Not recorded | 69dc78627d0172140ec7891f | ### ImageProtector Refusal Rate: 81. Result ID: 69dcaac147f34ce924c3a179. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"Phi-4-multimodal","Shadow Question Type":"general probing questions","Question Relevance":"image-irrelevant"}. This record does not assert independent reproduction. ### ImageProtector Refusal Rate: 85. Result ID: 69dcaac147f34ce924c3a1c6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"Phi-4-multimodal","Shadow Question Type":"similar","Question Relevance":"image-irrelevant"}. This record does not assert independent reproduction. ### ImageProtector Refusal Rate: 86. Result ID: 69dcaac147f34ce924c3a177. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"Qwen-VL-Chat","Shadow Question Type":"general probing questions","Question Relevance":"image-irrelevant"}. This record does not assert independent reproduction. ### ImageProtector Refusal Rate: 87. Result ID: 69dcaac147f34ce924c3a161. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"Phi-4-multimodal","Shadow Question Type":"Similar probing questions","Question Relevance":"Image-relevant"}. This record does not assert independent reproduction. ### ImageProtector Refusal Rate: 87. Result ID: 69dcaac147f34ce924c3a178. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"InstructBLIP","Shadow Question Type":"general probing questions","Question Relevance":"image-irrelevant"}. This record does not assert independent reproduction. ### ImageProtector Refusal Rate: 87. Result ID: 69dcaac147f34ce924c3a17a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"Qwen2.5-VL","Shadow Question Type":"general probing questions","Question Relevance":"image-irrelevant"}. This record does not assert independent reproduction. ### ImageProtector Refusal Rate: 87. Result ID: 69dcaac147f34ce924c3a1c5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"InstructBLIP","Shadow Question Type":"similar","Question Relevance":"image-irrelevant"}. This record does not assert independent reproduction. ### ImageProtector Refusal Rate: 89. Result ID: 69dcaac147f34ce924c3a160. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"InstructBLIP","Shadow Question Type":"Similar probing questions","Question Relevance":"Image-relevant"}. This record does not assert independent reproduction. ### ImageProtector Refusal Rate: 90. Result ID: 69dcaac147f34ce924c3a195. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"InstructBLIP","Probing Question Type":"exact","Question Relevance":"image-irrelevant"}. This record does not assert independent reproduction. ### ImageProtector Refusal Rate: 93. Result ID: 69dcaac147f34ce924c3a1ad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"InstructBLIP","Shadow Question Type":"exact","Question Relevance":"image-relevant"}. This record does not assert independent reproduction. ### ImageProtector Refusal Rate: 94. Result ID: 69dcaac147f34ce924c3a194. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"Qwen-VL-Chat","Probing Question Type":"exact","Question Relevance":"image-irrelevant"}. This record does not assert independent reproduction. ### ImageProtector Refusal Rate: 94. Result ID: 69dcaac147f34ce924c3a1c2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"LLaVA-1.5","Shadow Question Type":"similar","Question Relevance":"image-irrelevant"}. This record does not assert independent reproduction. ### ImageProtector Refusal Rate: 94. Result ID: 69dcaac147f34ce924c3a1c7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"Qwen2.5-VL","Shadow Question Type":"similar","Question Relevance":"image-irrelevant"}. This record does not assert independent reproduction. ### ImageProtector Refusal Rate: 95. Result ID: 69dcaac147f34ce924c3a162. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"Qwen2.5-VL","Shadow Question Type":"Similar probing questions","Question Relevance":"Image-relevant"}. This record does not assert independent reproduction. ### ImageProtector Refusal Rate: 95. Result ID: 69dcaac147f34ce924c3a176. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"MiniGPT-4","Shadow Question Type":"general probing questions","Question Relevance":"image-irrelevant"}. This record does not assert independent reproduction. ### ImageProtector Refusal Rate: 96. Result ID: 69dcaac147f34ce924c3a193. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"MiniGPT-4","Probing Question Type":"exact","Question Relevance":"image-irrelevant"}. This record does not assert independent reproduction. ### ImageProtector Refusal Rate: 96. Result ID: 69dcaac147f34ce924c3a1c4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"Qwen-VL-Chat","Shadow Question Type":"similar","Question Relevance":"image-irrelevant"}. This record does not assert independent reproduction. ### ImageProtector Refusal Rate: 97. Result ID: 69dcaac147f34ce924c3a175. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"LLaVA-1.5","Shadow Question Type":"general probing questions","Question Relevance":"image-irrelevant"}. This record does not assert independent reproduction. ### ImageProtector Refusal Rate: 97. Result ID: 69dcaac147f34ce924c3a1ab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"MiniGPT-4","Shadow Question Type":"exact","Question Relevance":"image-relevant"}. This record does not assert independent reproduction. ### ImageProtector Refusal Rate: 98. Result ID: 69dcaac047f34ce924c3a15e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"MiniGPT-4","Shadow Question Type":"Similar probing questions","Question Relevance":"Image-relevant"}. This record does not assert independent reproduction. ### ImageProtector Refusal Rate: 98. Result ID: 69dcaac047f34ce924c3a15f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"Qwen-VL-Chat","Shadow Question Type":"Similar probing questions","Question Relevance":"Image-relevant"}. This record does not assert independent reproduction. ### ImageProtector Refusal Rate: 98. Result ID: 69dcaac147f34ce924c3a192. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"LLaVA-1.5","Probing Question Type":"exact","Question Relevance":"image-irrelevant"}. This record does not assert independent reproduction. ### ImageProtector Refusal Rate: 99. Result ID: 69dcaac147f34ce924c3a1ac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"Qwen-VL-Chat","Shadow Question Type":"exact","Question Relevance":"image-relevant"}. This record does not assert independent reproduction. ### ImageProtector Refusal Rate: 99. Result ID: 69dcaac147f34ce924c3a1c3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"MiniGPT-4","Shadow Question Type":"similar","Question Relevance":"image-irrelevant"}. This record does not assert independent reproduction. ### ImageProtector Refusal Rate: 100. Result ID: 69dcaac047f34ce924c3a15d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"LLaVA-1.5","Shadow Question Type":"Similar probing questions","Question Relevance":"Image-relevant"}. This record does not assert independent reproduction. ### ImageProtector Refusal Rate: 100. Result ID: 69dcaac147f34ce924c3a196. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"Phi-4-multimodal","Probing Question Type":"exact","Question Relevance":"image-irrelevant"}. This record does not assert independent reproduction. ### ImageProtector Refusal Rate: 100. Result ID: 69dcaac147f34ce924c3a197. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"Qwen2.5-VL","Probing Question Type":"exact","Question Relevance":"image-irrelevant"}. This record does not assert independent reproduction. ### ImageProtector Refusal Rate: 100. Result ID: 69dcaac147f34ce924c3a1aa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"LLaVA-1.5","Shadow Question Type":"exact","Question Relevance":"image-relevant"}. This record does not assert independent reproduction. ### ImageProtector Refusal Rate: 100. Result ID: 69dcaac147f34ce924c3a1ae. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"Phi-4-multimodal","Shadow Question Type":"exact","Question Relevance":"image-relevant"}. This record does not assert independent reproduction. ### ImageProtector Refusal Rate: 100. Result ID: 69dcaac147f34ce924c3a1af. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target MLLM":"Qwen2.5-VL","Shadow Question Type":"exact","Question Relevance":"image-relevant"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.