# Image Classification on MNIST (Clean Accuracy, Adversarial Accuracy, AURAC) Source: [Image Classification on MNIST (Clean Accuracy, Adversarial Accuracy, AURAC)]() Collection index: [llms.txt]() Data updated: 2026-05-11T07:43:33.052Z Evaluation of Image Classification performance on the MNIST dataset, specifically focusing on robustness metrics including Clean Accuracy, Adversarial Accuracy (at epsilon 0.30), and AURAC. 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) | MNIST | | Metric | Clean Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 7 of 7 | | 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 - [Clean Accuracy](): Higher is better; unit: PERCENT. - [Adversarial Accuracy (eps=0.30)](): Higher is better; unit: PERCENT. - [AURAC](): Higher is better; unit: PERCENT. - [Dataset Size (Samples)](): Higher is better; unit: SIZE. ## Recorded results | Method | Clean Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Vanilla | 94.9 | Not recorded | 6a01628edbc836b87d8230b7 | | Selective | 94.9 | Not recorded | 6a01628edbc836b87d8230b7 | | AdvTrain | 94.5 | Not recorded | 6a01628edbc836b87d8230b7 | | Selective | 94.5 | Not recorded | 6a01628edbc836b87d8230b7 | | Two-Stage Sel. | 94.5 | Not recorded | 6a01628edbc836b87d8230b7 | | Sep-Aware | 94.2 | Not recorded | 6a01628edbc836b87d8230b7 | | AdvTrain | 94.1 | Not recorded | 6a01628edbc836b87d8230b7 | ### Vanilla Clean Accuracy: 94.9. Result ID: 6a01888f47f34ce924e30fc0. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Selective Clean Accuracy: 94.9. Result ID: 6a01888f47f34ce924e30fc4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Selective Mechanism":"on"}. This record does not assert independent reproduction. ### AdvTrain Clean Accuracy: 94.5. Result ID: 6a01888f47f34ce924e30fc1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Adversarial Training":"off"}. This record does not assert independent reproduction. ### Selective Clean Accuracy: 94.5. Result ID: 6a01888f47f34ce924e30fc3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Selective Mechanism":"off"}. This record does not assert independent reproduction. ### Two-Stage Sel. Clean Accuracy: 94.5. Result ID: 6a01888f47f34ce924e30fc6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Sep-Aware Clean Accuracy: 94.2. Result ID: 6a01888f47f34ce924e30fc5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### AdvTrain Clean Accuracy: 94.1. Result ID: 6a01888f47f34ce924e30fc2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Adversarial Training":"on"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.