# Image Classification on CIFAR-100 (Clean and Robust Accuracy) Source: [Image Classification on CIFAR-100 (Clean and Robust Accuracy)]() Collection index: [llms.txt]() Data updated: 2026-05-12T08:40:40.204Z Evaluation of Image Classification performance on the CIFAR-100 dataset, reporting both standard Clean Accuracy and Robust Accuracy 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) | CIFAR-100 | | Metric | Clean Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 10 of 10 | | 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. - [Robust Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Clean Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Default | 81.55 | Not recorded | 6a02b429dbc836b87d824739 | | TARO-3-AA | 74.72 | Not recorded | 6a02b429dbc836b87d824739 | | Score-Opt-N | 74.18 | Not recorded | 6a02b429dbc836b87d824739 | | TARO-2 | 73.78 | Not recorded | 6a02b429dbc836b87d824739 | | TARO-2-AA | 72.76 | Not recorded | 6a02b429dbc836b87d824739 | | TARO-3 | 72.61 | Not recorded | 6a02b429dbc836b87d824739 | | Score-Opt-O | 70.53 | Not recorded | 6a02b429dbc836b87d824739 | | AAOpt | 69.68 | Not recorded | 6a02b429dbc836b87d824739 | | Yoon et al. \[2021\] | 60.66 | Not recorded | 6a02b429dbc836b87d824739 | | Hill et al. \[2021\] | 51.66 | Not recorded | 6a02b429dbc836b87d824739 | ### Default Clean Accuracy: 81.55. Result ID: 6a02e61b47f34ce924e5b024. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"WRN-28-10","Attack type":"BPDA+EOT","Perturbation type (l\_infinity)":"l\_infinity","Perturbation budget (epsilon)":"8/255"}. This record does not assert independent reproduction. ### TARO-3-AA Clean Accuracy: 74.72. Result ID: 6a02e61b47f34ce924e5b02d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"WRN-28-10","Attack type":"BPDA+EOT","Perturbation type (l\_infinity)":"l\_infinity","Perturbation budget (epsilon)":"8/255"}. This record does not assert independent reproduction. ### Score-Opt-N Clean Accuracy: 74.18. Result ID: 6a02e61b47f34ce924e5b028. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"WRN-28-10","Attack type":"BPDA+EOT","Perturbation type (l\_infinity)":"l\_infinity","Perturbation budget (epsilon)":"8/255"}. This record does not assert independent reproduction. ### TARO-2 Clean Accuracy: 73.78. Result ID: 6a02e61b47f34ce924e5b02a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"WRN-28-10","Attack type":"BPDA+EOT","Perturbation type (l\_infinity)":"l\_infinity","Perturbation budget (epsilon)":"8/255"}. This record does not assert independent reproduction. ### TARO-2-AA Clean Accuracy: 72.76. Result ID: 6a02e61b47f34ce924e5b02c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"WRN-28-10","Attack type":"BPDA+EOT","Perturbation type (l\_infinity)":"l\_infinity","Perturbation budget (epsilon)":"8/255"}. This record does not assert independent reproduction. ### TARO-3 Clean Accuracy: 72.61. Result ID: 6a02e61b47f34ce924e5b02b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"WRN-28-10","Attack type":"BPDA+EOT","Perturbation type (l\_infinity)":"l\_infinity","Perturbation budget (epsilon)":"8/255"}. This record does not assert independent reproduction. ### Score-Opt-O Clean Accuracy: 70.53. Result ID: 6a02e61b47f34ce924e5b027. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"WRN-28-10","Attack type":"BPDA+EOT","Perturbation type (l\_infinity)":"l\_infinity","Perturbation budget (epsilon)":"8/255"}. This record does not assert independent reproduction. ### AAOpt Clean Accuracy: 69.68. Result ID: 6a02e61b47f34ce924e5b029. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"WRN-28-10","Attack type":"BPDA+EOT","Perturbation type (l\_infinity)":"l\_infinity","Perturbation budget (epsilon)":"8/255"}. This record does not assert independent reproduction. ### Yoon et al. \[2021\] Clean Accuracy: 60.66. Result ID: 6a02e61b47f34ce924e5b025. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"WRN-28-10","Attack type":"BPDA+EOT","Perturbation type (l\_infinity)":"l\_infinity","Perturbation budget (epsilon)":"8/255"}. This record does not assert independent reproduction. ### Hill et al. \[2021\] Clean Accuracy: 51.66. Result ID: 6a02e61b47f34ce924e5b026. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"WRN-28-10","Attack type":"BPDA+EOT","Perturbation type (l\_infinity)":"l\_infinity","Perturbation budget (epsilon)":"8/255"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.