# Image Classification on GTSRB (test) (Clean Acc & ASR Deltas) Source: [Image Classification on GTSRB (test) (Clean Acc & ASR Deltas)]() Collection index: [llms.txt]() Data updated: 2026-06-26T07:36:02.921Z Evaluation of Image Classification performance on the test split of the German Traffic Sign Recognition Benchmark (GTSRB), focusing on Clean Accuracy, Attack Success Rate (ASR), and the calculated deltas for these metrics. 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) | GTSRB (test) | | Metric | Clean Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 8 of 8 | | 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. - [Attack Success Rate](): Higher is better; unit: PERCENT. - [Clean Accuracy Delta](): Lower is better; unit: SCALAR. - [ASR Delta](): Lower is better; unit: SCALAR. ## Recorded results | Method | Clean Accuracy | Result date | Report paper | | --- | --- | --- | --- | | clean data | 98.76 | Not recorded | 6a3e0765206542251d7cb32d | | same-class | 98.31 | Not recorded | 6a3e0765206542251d7cb32d | | clean data | 98.22 | Not recorded | 6a3e0765206542251d7cb32d | | one-to-one | 97.83 | Not recorded | 6a3e0765206542251d7cb32d | | all-to-one | 97.59 | Not recorded | 6a3e0765206542251d7cb32d | | same-class | 97.25 | Not recorded | 6a3e0765206542251d7cb32d | | one-to-one | 96.67 | Not recorded | 6a3e0765206542251d7cb32d | | all-to-one | 96.55 | Not recorded | 6a3e0765206542251d7cb32d | ### clean data Clean Accuracy: 98.76. Result ID: 6a3e2bc9fbc373592c5f4e9c. [Reporting paper]() Recorded evaluation configuration: {"Sampler":"DDIM","Backbone":"ResNet"}. This record does not assert independent reproduction. ### same-class Clean Accuracy: 98.31. Result ID: 6a3e2bc9fbc373592c5f4e9a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sampler":"DDPM","Backbone":"ResNet"}. This record does not assert independent reproduction. ### clean data Clean Accuracy: 98.22. Result ID: 6a3e2bc9fbc373592c5f4e98. [Reporting paper]() Recorded evaluation configuration: {"Sampler":"DDPM","Backbone":"ResNet"}. This record does not assert independent reproduction. ### one-to-one Clean Accuracy: 97.83. Result ID: 6a3e2bc9fbc373592c5f4e99. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sampler":"DDPM","Backbone":"ResNet"}. This record does not assert independent reproduction. ### all-to-one Clean Accuracy: 97.59. Result ID: 6a3e2bc9fbc373592c5f4e9b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sampler":"DDPM","Backbone":"ResNet"}. This record does not assert independent reproduction. ### same-class Clean Accuracy: 97.25. Result ID: 6a3e2bc9fbc373592c5f4e9e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sampler":"DDIM","Backbone":"ResNet"}. This record does not assert independent reproduction. ### one-to-one Clean Accuracy: 96.67. Result ID: 6a3e2bc9fbc373592c5f4e9d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sampler":"DDIM","Backbone":"ResNet"}. This record does not assert independent reproduction. ### all-to-one Clean Accuracy: 96.55. Result ID: 6a3e2bc9fbc373592c5f4e9f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sampler":"DDIM","Backbone":"ResNet"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.