# Image Classification Robustness on Cifar100 (CW, PGD, Auto Attack) Source: [Image Classification Robustness on Cifar100 (CW, PGD, Auto Attack)]() Collection index: [llms.txt]() Data updated: 2026-02-27T11:46:08.907Z Evaluation of Image Classification performance on the Cifar100 dataset under adversarial attacks, reporting accuracy for Clean data and specific attacks: PGD, CW, and Auto Attack. 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) | Cifar100 | | Metric | Accuracy (Clean) | | 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 - [Accuracy (Clean)](): Higher is better; unit: PERCENT. - [Error Rate (PGD)](): Lower is better; unit: PERCENT. - [Error Rate (CW)](): Lower is better; unit: PERCENT. - [Error Rate (Auto Attack)](): Lower is better; unit: PERCENT. ## Recorded results | Method | Accuracy (Clean) | Result date | Report paper | | --- | --- | --- | --- | | CLIP | 60.45 | Not recorded | 6940e7a8456146936284f897 | | UCAT | 54.45 | Not recorded | 6940e7a8456146936284f897 | | FARE | 48.27 | Not recorded | 6940e7a8456146936284f897 | | TGA-ZSR | 47.37 | Not recorded | 6940e7a8456146936284f897 | | PMG-AFT | 43.59 | Not recorded | 6940e7a8456146936284f897 | | TeCoA | 38.26 | Not recorded | 6940e7a8456146936284f897 | ### CLIP Accuracy (Clean): 60.45. Result ID: 69a183f135dfcabb00e78903. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### UCAT Accuracy (Clean): 54.45. Result ID: 69a183f135dfcabb00e78908. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning dataset":"TinyImageNet","Adversarial training":"2-step PGD","Epsilon":"1/255"}. This record does not assert independent reproduction. ### FARE Accuracy (Clean): 48.27. Result ID: 69a183f135dfcabb00e78905. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning dataset":"TinyImageNet","Adversarial training":"2-step PGD","Epsilon":"1/255"}. This record does not assert independent reproduction. ### TGA-ZSR Accuracy (Clean): 47.37. Result ID: 69a183f135dfcabb00e78907. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Fine-tuning dataset":"TinyImageNet","Adversarial training":"2-step PGD","Epsilon":"1/255"}. This record does not assert independent reproduction. ### PMG-AFT Accuracy (Clean): 43.59. Result ID: 69a183f135dfcabb00e78906. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning dataset":"TinyImageNet","Adversarial training":"2-step PGD","Epsilon":"1/255"}. This record does not assert independent reproduction. ### TeCoA Accuracy (Clean): 38.26. Result ID: 69a183f135dfcabb00e78904. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning dataset":"TinyImageNet","Adversarial training":"2-step PGD","Epsilon":"1/255"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.