# Image Classification on CIFAR-100 (Adversarial Robustness Metrics) Source: [Image Classification on CIFAR-100 (Adversarial Robustness Metrics)]() Collection index: [llms.txt]() Data updated: 2026-04-14T10:34:32.619Z Evaluation of Image Classification performance on the CIFAR-100 dataset, focusing on robustness against various adversarial attacks including FGSM, PGD, BIM, APGD, and Jitter at specified perturbation budgets. 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 | Acc (FGSM, 8/255) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 7 of 7 | | 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 - [Acc (FGSM, 8/255)](): Higher is better; unit: PERCENT. - [Acc (FGSM, 16/255)](): Higher is better; unit: PERCENT. - [Acc (PGD, 8/255)](): Higher is better; unit: PERCENT. - [Acc (PGD, 16/255)](): Higher is better; unit: PERCENT. - [Acc (BIM, 8/255)](): Higher is better; unit: PERCENT. - [Acc (BIM, 16/255)](): Higher is better; unit: PERCENT. - [Acc (APGD, 8/255)](): Higher is better; unit: PERCENT. - [Acc (APGD, 16/255)](): Higher is better; unit: PERCENT. - [Acc (Jitter, 8/255)](): Higher is better; unit: PERCENT. - [Acc (Jitter, 16/255)](): Higher is better; unit: PERCENT. - [Avg Robust Acc](): Higher is better; unit: PERCENT. ## Recorded results | Method | Acc (FGSM, 8/255) | Result date | Report paper | | --- | --- | --- | --- | | FxTS-Net | 19.99 | Not recorded | 68fa5e551e209131ce9e165d | | Zubov-Net | 19.53 | Not recorded | 68fa5e551e209131ce9e165d | | Proj-NODE | 18.86 | Not recorded | 68fa5e551e209131ce9e165d | | LyaNet | 18.3 | Not recorded | 68fa5e551e209131ce9e165d | | SODEF | 17.57 | Not recorded | 68fa5e551e209131ce9e165d | | ResNet18 | 16.97 | Not recorded | 68fa5e551e209131ce9e165d | | Neural ODE | 16.24 | Not recorded | 68fa5e551e209131ce9e165d | ### FxTS-Net Acc (FGSM, 8/255): 19.99. Result ID: 69de183147f34ce924c63c80. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Zubov-Net Acc (FGSM, 8/255): 19.53. Result ID: 69de183147f34ce924c63c82. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Proj-NODE Acc (FGSM, 8/255): 18.86. Result ID: 69de183147f34ce924c63c7e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LyaNet Acc (FGSM, 8/255): 18.3. Result ID: 69de183147f34ce924c63c81. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SODEF Acc (FGSM, 8/255): 17.57. Result ID: 69de183147f34ce924c63c7f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### ResNet18 Acc (FGSM, 8/255): 16.97. Result ID: 69de183147f34ce924c63c7c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Neural ODE Acc (FGSM, 8/255): 16.24. Result ID: 69de183147f34ce924c63c7d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.