# Image Classification on CIFAR-10 l\_inf = 8/255 (test) Source: [Image Classification on CIFAR-10 l\_inf = 8/255 (test)]() Collection index: [llms.txt]() Data updated: 2026-06-02T11:59:22.999Z Evaluation of Image Classification performance on the CIFAR-10 test set under an L-infinity adversarial threat model with epsilon set to 8/255, reporting both clean and robust accuracy. 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 l\_inf = 8/255 (test) | | Metric | Clean Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 8 of 8 | | 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 | | --- | --- | --- | --- | | Bartoldson | 93.7 | Not recorded | 6a1e6433dbd7150506f8581d | | Wang | 93.4 | Not recorded | 6a1e6433dbd7150506f8581d | | Cui | 92.9 | Not recorded | 6a1e6433dbd7150506f8581d | | Wang | 92 | Not recorded | 6a1e6433dbd7150506f8581d | | Bartoldson | 91.9 | Not recorded | 6a1e6433dbd7150506f8581d | | Cui | 91.8 | Not recorded | 6a1e6433dbd7150506f8581d | | Jia | 85.3 | Not recorded | 6a1e6433dbd7150506f8581d | | Jia | 82.8 | Not recorded | 6a1e6433dbd7150506f8581d | ### Bartoldson Clean Accuracy: 93.7. Result ID: 6a1ec58cfbc373592c1a41f3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Classifier Type":"fully-connected"}. This record does not assert independent reproduction. ### Wang Clean Accuracy: 93.4. Result ID: 6a1ec58cfbc373592c1a41f1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Classifier Type":"fully-connected"}. This record does not assert independent reproduction. ### Cui Clean Accuracy: 92.9. Result ID: 6a1ec58cfbc373592c1a41f0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Classifier Type":"fully-connected"}. This record does not assert independent reproduction. ### Wang Clean Accuracy: 92. Result ID: 6a1ec58cfbc373592c1a41f5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Classifier Type":"distance-based"}. This record does not assert independent reproduction. ### Bartoldson Clean Accuracy: 91.9. Result ID: 6a1ec58cfbc373592c1a41f7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Classifier Type":"distance-based"}. This record does not assert independent reproduction. ### Cui Clean Accuracy: 91.8. Result ID: 6a1ec58cfbc373592c1a41f4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Classifier Type":"distance-based"}. This record does not assert independent reproduction. ### Jia Clean Accuracy: 85.3. Result ID: 6a1ec58cfbc373592c1a41f2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Classifier Type":"fully-connected"}. This record does not assert independent reproduction. ### Jia Clean Accuracy: 82.8. Result ID: 6a1ec58cfbc373592c1a41f6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Classifier Type":"distance-based"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.