# Image Classification on CIFAR-10 (test) (Accuracy at Epsilon Levels) Source: [Image Classification on CIFAR-10 (test) (Accuracy at Epsilon Levels)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:34:34.617Z Image Classification evaluation on the CIFAR-10 test set, reporting accuracy under specific perturbation or uncertainty levels defined by epsilon (e.g., ε=0.2 and ε=0.3). 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 (test) | | Metric | Accuracy (ε=0.2) | | 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 - [Accuracy (ε=0.2)](): Higher is better; unit: PERCENT. - [Accuracy (ε=0.3)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (ε=0.2) | Result date | Report paper | | --- | --- | --- | --- | | CORES2 | 95.18 | Not recorded | 68fa698f1e209131cea22a5b | | SELF | 93.75 | Not recorded | 68fa698f1e209131cea22a5b | | NLNL | 93.35 | Not recorded | 68fa698f1e209131cea22a5b | | MAE | 89.67 | Not recorded | 68fa698f1e209131cea22a5b | | Forward T | 89.42 | Not recorded | 68fa698f1e209131cea22a5b | | Lq | 89.33 | Not recorded | 68fa698f1e209131cea22a5b | | LDMI | 89.04 | Not recorded | 68fa698f1e209131cea22a5b | | Cross Entropy | 88.59 | Not recorded | 68fa698f1e209131cea22a5b | ### CORES2 Accuracy (ε=0.2): 95.18. Result ID: 698db6708b517eb433234431. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SELF Accuracy (ε=0.2): 93.75. Result ID: 698db6708b517eb433234430. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### NLNL Accuracy (ε=0.2): 93.35. Result ID: 698db6708b517eb43323442f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MAE Accuracy (ε=0.2): 89.67. Result ID: 698db6708b517eb43323442b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Forward T Accuracy (ε=0.2): 89.42. Result ID: 698db6708b517eb43323442c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Lq Accuracy (ε=0.2): 89.33. Result ID: 698db6708b517eb43323442d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LDMI Accuracy (ε=0.2): 89.04. Result ID: 698db6708b517eb43323442e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Cross Entropy Accuracy (ε=0.2): 88.59. Result ID: 698db6708b517eb43323442a. [Reporting paper]() [Method origin paper]() 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.