# Image Classification on CIFAR-10 Distribution II: Quantity Skew (test) Source: [Image Classification on CIFAR-10 Distribution II: Quantity Skew (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:31:18.217Z Evaluation of Image Classification performance on the test split of the CIFAR-10 Distribution II dataset, which exhibits a quantity skew in class distribution. Metrics include Accuracy and Noise Scale. 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 Distribution II: Quantity Skew (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | 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](): Higher is better; unit: PERCENT. - [Noise Scale](): Lower is better; unit: SCALAR. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | No Protection | 45.16 | Not recorded | 695c970f53fdd5c36174382f | | LaDP-FL | 31.79 | Not recorded | 695c970f53fdd5c36174382f | | AdapLDP | 29.52 | Not recorded | 695c970f53fdd5c36174382f | | DPA LDP | 27.91 | Not recorded | 695c970f53fdd5c36174382f | | LaDP-FL | 26.86 | Not recorded | 695c970f53fdd5c36174382f | | Sensitive DP | 26.03 | Not recorded | 695c970f53fdd5c36174382f | | DPA LDP | 24.95 | Not recorded | 695c970f53fdd5c36174382f | | Sensitive DP | 21.39 | Not recorded | 695c970f53fdd5c36174382f | | Time-Varying DP | 20.94 | Not recorded | 695c970f53fdd5c36174382f | | AdapLDP | 19.1 | Not recorded | 695c970f53fdd5c36174382f | | Time-Varying DP | 17.77 | Not recorded | 695c970f53fdd5c36174382f | | Full DP | 17.33 | Not recorded | 695c970f53fdd5c36174382f | | Full DP | 15.13 | Not recorded | 695c970f53fdd5c36174382f | ### No Protection Accuracy: 45.16. Result ID: 6996f68b5698665ec4433f09. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### LaDP-FL Accuracy: 31.79. Result ID: 6996f68b5698665ec4433f15. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"0.5","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### AdapLDP Accuracy: 29.52. Result ID: 6996f68b5698665ec4433f14. [Reporting paper]() Recorded evaluation configuration: {"epsilon":"0.5","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### DPA LDP Accuracy: 27.91. Result ID: 6996f68b5698665ec4433f13. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"0.5","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### LaDP-FL Accuracy: 26.86. Result ID: 6996f68b5698665ec4433f0f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"0.2","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### Sensitive DP Accuracy: 26.03. Result ID: 6996f68b5698665ec4433f12. [Reporting paper]() Recorded evaluation configuration: {"epsilon":"0.5","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### DPA LDP Accuracy: 24.95. Result ID: 6996f68b5698665ec4433f0d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"0.2","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### Sensitive DP Accuracy: 21.39. Result ID: 6996f68b5698665ec4433f0c. [Reporting paper]() Recorded evaluation configuration: {"epsilon":"0.2","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### Time-Varying DP Accuracy: 20.94. Result ID: 6996f68b5698665ec4433f11. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"0.5","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### AdapLDP Accuracy: 19.1. Result ID: 6996f68b5698665ec4433f0e. [Reporting paper]() Recorded evaluation configuration: {"epsilon":"0.2","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### Time-Varying DP Accuracy: 17.77. Result ID: 6996f68b5698665ec4433f0b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"0.2","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### Full DP Accuracy: 17.33. Result ID: 6996f68b5698665ec4433f10. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"0.5","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### Full DP Accuracy: 15.13. Result ID: 6996f68b5698665ec4433f0a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"0.2","Backbone":"ResNet-18"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.