# Image Classification on ImageNet (val) (Natural and Adversarial Accuracy) Source: [Image Classification on ImageNet (val) (Natural and Adversarial Accuracy)]() Collection index: [llms.txt]() Data updated: 2026-05-08T11:04:59.506Z Evaluation of standard Image Classification performance on the ImageNet validation set, reporting both natural accuracy and accuracy under adversarial conditions. 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) | ImageNet (val) | | Metric | Natural Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 6 of 6 | | 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 - [Natural Accuracy](): Higher is better; unit: PERCENT. - [Adversarial Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Natural Accuracy | Result date | Report paper | | --- | --- | --- | --- | | MEFA | 82 | Not recorded | 69fd6e565497b3b670c896b3 | | MEFA | 81 | Not recorded | 69fd6e565497b3b670c896b3 | | MEFA | 77 | Not recorded | 69fd6e565497b3b670c896b3 | | MEFA | 75 | Not recorded | 69fd6e565497b3b670c896b3 | | DiffPure | 71.16 | Not recorded | 69fd6e565497b3b670c896b3 | | DiffPure | 67.79 | Not recorded | 69fd6e565497b3b670c896b3 | ### MEFA Natural Accuracy: 82. Result ID: 69fdc34f47f34ce924e19218. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Threat Model":"WideResNet-50-2","Hd":"1"}. This record does not assert independent reproduction. ### MEFA Natural Accuracy: 81. Result ID: 69fdc34f47f34ce924e19219. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Threat Model":"WideResNet-50-2","Hd":"50"}. This record does not assert independent reproduction. ### MEFA Natural Accuracy: 77. Result ID: 69fdc34f47f34ce924e19216. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Threat Model":"ResNet-50","Hd":"50"}. This record does not assert independent reproduction. ### MEFA Natural Accuracy: 75. Result ID: 69fdc34f47f34ce924e19215. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Threat Model":"ResNet-50","Hd":"1"}. This record does not assert independent reproduction. ### DiffPure Natural Accuracy: 71.16. Result ID: 69fdc34f47f34ce924e1921a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Threat Model":"WideResNet-50-2"}. This record does not assert independent reproduction. ### DiffPure Natural Accuracy: 67.79. Result ID: 69fdc34f47f34ce924e19217. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Threat Model":"ResNet-50"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.