# Image Classification on CIFAR-100 standard (test) (Certified Robustness) Source: [Image Classification on CIFAR-100 standard (test) (Certified Robustness)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:34:27.207Z Evaluation of Image Classification performance on the CIFAR-100 test set, reporting standard accuracy alongside certified accuracy under varying levels of input perturbation bounds (e.g., L-infinity bounds up to 108/255). 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 standard (test) | | Metric | Accuracy (Standard) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 (Standard)](): Higher is better; unit: PERCENT. - [Certified Accuracy (L-inf 36/255)](): Higher is better; unit: PERCENT. - [Certified Accuracy (L-inf 72/255)](): Higher is better; unit: PERCENT. - [Certified Accuracy (L-inf 108/255)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (Standard) | Result date | Report paper | | --- | --- | --- | --- | | LOT | 49.18 | Not recorded | 68fa6ee71e209131cea42cbd | | LOT | 48.99 | Not recorded | 68fa6ee71e209131cea42cbd | | LOT | 48.93 | Not recorded | 68fa6ee71e209131cea42cbd | | LOT | 48.81 | Not recorded | 68fa6ee71e209131cea42cbd | | LOT | 48.7 | Not recorded | 68fa6ee71e209131cea42cbd | | LOT | 48.38 | Not recorded | 68fa6ee71e209131cea42cbd | | LOT | 48.31 | Not recorded | 68fa6ee71e209131cea42cbd | | LOT | 48.25 | Not recorded | 68fa6ee71e209131cea42cbd | | SOC | 47.84 | Not recorded | 68fa6ee71e209131cea42cbd | | SOC | 47.61 | Not recorded | 68fa6ee71e209131cea42cbd | | SOC | 47.07 | Not recorded | 68fa6ee71e209131cea42cbd | | SOC | 46.92 | Not recorded | 68fa6ee71e209131cea42cbd | | SOC | 46.88 | Not recorded | 68fa6ee71e209131cea42cbd | | SOC | 46.87 | Not recorded | 68fa6ee71e209131cea42cbd | | SOC | 45.82 | Not recorded | 68fa6ee71e209131cea42cbd | | SOC | 45.03 | Not recorded | 68fa6ee71e209131cea42cbd | ### LOT Accuracy (Standard): 49.18. Result ID: 699083553a6c3148490119e9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"LipConvnet-30","Mean Evaluation Time (sec)":2.755,"LLN":true,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### LOT Accuracy (Standard): 48.99. Result ID: 699083553a6c3148490119e3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"LipConvnet-15","Mean Evaluation Time (sec)":1.627,"LLN":true,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### LOT Accuracy (Standard): 48.93. Result ID: 699083553a6c3148490119e7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"LipConvnet-25","Mean Evaluation Time (sec)":2.387,"LLN":true,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### LOT Accuracy (Standard): 48.81. Result ID: 699083553a6c3148490119e5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"LipConvnet-20","Mean Evaluation Time (sec)":1.962,"LLN":true,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### LOT Accuracy (Standard): 48.7. Result ID: 699083553a6c3148490119e1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"LipConvnet-10","Mean Evaluation Time (sec)":1.563,"LLN":true,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### LOT Accuracy (Standard): 48.38. Result ID: 699083553a6c3148490119df. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"LipConvnet-5","Mean Evaluation Time (sec)":1.411,"LLN":true,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### LOT Accuracy (Standard): 48.31. Result ID: 699083553a6c3148490119ed. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"LipConvnet-40","Mean Evaluation Time (sec)":3.595,"LLN":true,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### LOT Accuracy (Standard): 48.25. Result ID: 699083553a6c3148490119eb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"LipConvnet-35","Mean Evaluation Time (sec)":3.193,"LLN":true,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### SOC Accuracy (Standard): 47.84. Result ID: 699083553a6c3148490119e4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"LipConvnet-20","Mean Evaluation Time (sec)":5.142,"LLN":true,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### SOC Accuracy (Standard): 47.61. Result ID: 699083553a6c3148490119e2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"LipConvnet-15","Mean Evaluation Time (sec)":4.105,"LLN":true,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### SOC Accuracy (Standard): 47.07. Result ID: 699083553a6c3148490119e0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"LipConvnet-10","Mean Evaluation Time (sec)":3.342,"LLN":true,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### SOC Accuracy (Standard): 46.92. Result ID: 699083553a6c3148490119e8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"LipConvnet-30","Mean Evaluation Time (sec)":6.927,"LLN":true,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### SOC Accuracy (Standard): 46.88. Result ID: 699083553a6c3148490119ea. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"LipConvnet-35","Mean Evaluation Time (sec)":7.87,"LLN":true,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### SOC Accuracy (Standard): 46.87. Result ID: 699083553a6c3148490119e6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"LipConvnet-25","Mean Evaluation Time (sec)":6.087,"LLN":true,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### SOC Accuracy (Standard): 45.82. Result ID: 699083553a6c3148490119de. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"LipConvnet-5","Mean Evaluation Time (sec)":2.285,"LLN":true,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### SOC Accuracy (Standard): 45.03. Result ID: 699083553a6c3148490119ec. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"LipConvnet-40","Mean Evaluation Time (sec)":8.668,"LLN":true,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.