# Image Classification (Certified Robustness) on CelebA (test) Source: [Image Classification (Certified Robustness) on CelebA (test)]() Collection index: [llms.txt]() Data updated: 2026-05-29T08:02:54.020Z Evaluation of certified adversarial robustness for image classification models on the test split of the CelebA dataset, reporting accuracy across various perturbation radii (r). 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 | Image Classification | | Dataset (including any stated split) | CelebA (test) | | Metric | Certified Accuracy (r=0.00) | | Unit | PERCENT | | Direction | Higher 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 - [Certified Accuracy (r=0.00)](): Higher is better; unit: PERCENT. - [Certified Accuracy (r=0.10)](): Higher is better; unit: PERCENT. - [Certified Accuracy (r=0.20)](): Higher is better; unit: PERCENT. - [Certified Accuracy (r=0.30)](): Higher is better; unit: PERCENT. - [Certified Accuracy (r=0.40)](): Higher is better; unit: PERCENT. - [Certified Accuracy (r=0.50)](): Higher is better; unit: PERCENT. - [Certified Accuracy (r=0.60)](): Higher is better; unit: PERCENT. - [Certified Accuracy (r=0.70)](): Higher is better; unit: PERCENT. - [Certified Accuracy (r=0.80)](): Higher is better; unit: PERCENT. - [Certified Accuracy (r=0.90)](): Higher is better; unit: PERCENT. - [ACR](): Higher is better; unit: PERCENT. ## Recorded results | Method | Certified Accuracy (r=0.00) | Result date | Report paper | | --- | --- | --- | --- | | GLEAN | 56 | Not recorded | 68fa771f1e209131cea71380 | | Gaussian | 32 | Not recorded | 68fa771f1e209131cea71380 | | SmoothAdv | 29 | Not recorded | 68fa771f1e209131cea71380 | | Consistency | 24 | Not recorded | 68fa771f1e209131cea71380 | | MACER | 23 | Not recorded | 68fa771f1e209131cea71380 | ### GLEAN Certified Accuracy (r=0.00): 56. Result ID: 6a194749fbc373592c1374d0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":"0.25"}. This record does not assert independent reproduction. ### Gaussian Certified Accuracy (r=0.00): 32. Result ID: 6a194749fbc373592c1374cc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":"0.25"}. This record does not assert independent reproduction. ### SmoothAdv Certified Accuracy (r=0.00): 29. Result ID: 6a194749fbc373592c1374ce. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":"0.25"}. This record does not assert independent reproduction. ### Consistency Certified Accuracy (r=0.00): 24. Result ID: 6a194749fbc373592c1374cf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":"0.25"}. This record does not assert independent reproduction. ### MACER Certified Accuracy (r=0.00): 23. Result ID: 6a194749fbc373592c1374cd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":"0.25"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.