# Image Classification on ImageNet (Top-1 Clean and Robust Accuracy) Source: [Image Classification on ImageNet (Top-1 Clean and Robust Accuracy)]() Collection index: [llms.txt]() Data updated: 2026-05-26T13:12:38.332Z Evaluation of Image Classification performance on the standard ImageNet dataset, reporting both Top-1 Clean Accuracy and Top-1 Robust Accuracy. 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 | | Metric | Top-1 Clean Accuracy | | 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 - [Top-1 Clean Accuracy](): Higher is better; unit: PERCENT. - [Top-1 Robust Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Top-1 Clean Accuracy | Result date | Report paper | | --- | --- | --- | --- | | CLBP | 68.42 | Not recorded | 6a152978dbd7150506f7e433 | | AdvVLP | 53.23 | Not recorded | 6a152978dbd7150506f7e433 | | AdvMaPLe | 52.93 | Not recorded | 6a152978dbd7150506f7e433 | | FAP | 52.53 | Not recorded | 6a152978dbd7150506f7e433 | | AdvVP | 46.27 | Not recorded | 6a152978dbd7150506f7e433 | ### CLBP Top-1 Clean Accuracy: 68.42. Result ID: 6a159c35fbc373592c0e9380. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Shots":"16","Training Epochs":"10","Training Attack (PGD)":"2-step (1/255)","Evaluation Attack (PGD-100)":"100-step (1/255)"}. This record does not assert independent reproduction. ### AdvVLP Top-1 Clean Accuracy: 53.23. Result ID: 6a159c35fbc373592c0e937d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Shots":"16","Training Epochs":"10","Training Attack (PGD)":"2-step (1/255)","Evaluation Attack (PGD-100)":"100-step (1/255)"}. This record does not assert independent reproduction. ### AdvMaPLe Top-1 Clean Accuracy: 52.93. Result ID: 6a159c35fbc373592c0e937e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Shots":"16","Training Epochs":"10","Training Attack (PGD)":"2-step (1/255)","Evaluation Attack (PGD-100)":"100-step (1/255)"}. This record does not assert independent reproduction. ### FAP Top-1 Clean Accuracy: 52.53. Result ID: 6a159c35fbc373592c0e937f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Shots":"16","Training Epochs":"10","Training Attack (PGD)":"2-step (1/255)","Evaluation Attack (PGD-100)":"100-step (1/255)"}. This record does not assert independent reproduction. ### AdvVP Top-1 Clean Accuracy: 46.27. Result ID: 6a159c35fbc373592c0e937c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Shots":"16","Training Epochs":"10","Training Attack (PGD)":"2-step (1/255)","Evaluation Attack (PGD-100)":"100-step (1/255)"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.