# Image Classification on CIFAR-10 standard (test) (Certified Robustness Metrics) Source: [Image Classification on CIFAR-10 standard (test) (Certified Robustness Metrics)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:08:10.726Z Evaluation of Image Classification performance on the CIFAR-10 standard test set, reporting vanilla accuracy alongside certified accuracy thresholds. 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-10 standard (test) | | Metric | Vanilla Accuracy | | 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 - [Vanilla Accuracy](): Higher is better; unit: PERCENT. - [Certified Accuracy (36/255)](): Higher is better; unit: PERCENT. - [Certified Accuracy (72/255)](): Higher is better; unit: PERCENT. - [Certified Accuracy (108/255)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Vanilla Accuracy | Result date | Report paper | | --- | --- | --- | --- | | LOT | 77.12 | Not recorded | 68fa6ee71e209131cea42cbd | | LOT | 77.12 | Not recorded | 68fa6ee71e209131cea42cbd | | LOT | 76.91 | Not recorded | 68fa6ee71e209131cea42cbd | | LOT | 76.86 | Not recorded | 68fa6ee71e209131cea42cbd | | LOT | 76.83 | Not recorded | 68fa6ee71e209131cea42cbd | | LOT | 76.75 | Not recorded | 68fa6ee71e209131cea42cbd | | LOT | 76.5 | Not recorded | 68fa6ee71e209131cea42cbd | | SOC | 76.39 | Not recorded | 68fa6ee71e209131cea42cbd | | LOT | 76.34 | Not recorded | 68fa6ee71e209131cea42cbd | | SOC | 76.34 | Not recorded | 68fa6ee71e209131cea42cbd | | SOC | 76.23 | Not recorded | 68fa6ee71e209131cea42cbd | | SOC | 75.31 | Not recorded | 68fa6ee71e209131cea42cbd | | SOC | 75.21 | Not recorded | 68fa6ee71e209131cea42cbd | | SOC | 74.25 | Not recorded | 68fa6ee71e209131cea42cbd | | SOC | 74.23 | Not recorded | 68fa6ee71e209131cea42cbd | | SOC | 72.59 | Not recorded | 68fa6ee71e209131cea42cbd | ### LOT Vanilla Accuracy: 77.12. Result ID: 699083553a6c3148490119d5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"LipConvnet-20","Mean Evaluation Time (sec)":1.962,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### LOT Vanilla Accuracy: 77.12. Result ID: 699083553a6c3148490119d9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"LipConvnet-30","Mean Evaluation Time (sec)":2.755,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### LOT Vanilla Accuracy: 76.91. Result ID: 699083553a6c3148490119db. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"LipConvnet-35","Mean Evaluation Time (sec)":3.193,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### LOT Vanilla Accuracy: 76.86. Result ID: 699083553a6c3148490119d3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"LipConvnet-15","Mean Evaluation Time (sec)":1.627,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### LOT Vanilla Accuracy: 76.83. Result ID: 699083553a6c3148490119d7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"LipConvnet-25","Mean Evaluation Time (sec)":2.387,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### LOT Vanilla Accuracy: 76.75. Result ID: 699083553a6c3148490119dd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"LipConvnet-40","Mean Evaluation Time (sec)":3.595,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### LOT Vanilla Accuracy: 76.5. Result ID: 699083553a6c3148490119d1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"LipConvnet-10","Mean Evaluation Time (sec)":1.563,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### SOC Vanilla Accuracy: 76.39. Result ID: 699083553a6c3148490119d2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"LipConvnet-15","Mean Evaluation Time (sec)":4.105,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### LOT Vanilla Accuracy: 76.34. Result ID: 699083553a6c3148490119cf. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"LipConvnet-5","Mean Evaluation Time (sec)":1.411,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### SOC Vanilla Accuracy: 76.34. Result ID: 699083553a6c3148490119d4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"LipConvnet-20","Mean Evaluation Time (sec)":5.142,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### SOC Vanilla Accuracy: 76.23. Result ID: 699083553a6c3148490119d0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"LipConvnet-10","Mean Evaluation Time (sec)":3.342,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### SOC Vanilla Accuracy: 75.31. Result ID: 699083553a6c3148490119ce. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"LipConvnet-5","Mean Evaluation Time (sec)":2.285,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### SOC Vanilla Accuracy: 75.21. Result ID: 699083553a6c3148490119d6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"LipConvnet-25","Mean Evaluation Time (sec)":6.087,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### SOC Vanilla Accuracy: 74.25. Result ID: 699083553a6c3148490119da. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"LipConvnet-35","Mean Evaluation Time (sec)":7.87,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### SOC Vanilla Accuracy: 74.23. Result ID: 699083553a6c3148490119d8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"LipConvnet-30","Mean Evaluation Time (sec)":6.927,"CReg loss":true,"HH activation":true}. This record does not assert independent reproduction. ### SOC Vanilla Accuracy: 72.59. Result ID: 699083553a6c3148490119dc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"LipConvnet-40","Mean Evaluation Time (sec)":8.668,"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.