# Image Classification on CIFAR-10 (test) (Clean & BPDA20 Adversarial Accuracy) Source: [Image Classification on CIFAR-10 (test) (Clean & BPDA20 Adversarial Accuracy)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:39:18.444Z Evaluation of Image Classification performance on the CIFAR-10 test set, reporting standard clean accuracy alongside adversarial robustness measured using BPDA20-det 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 (test) | | Metric | Clean Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 7 of 7 | | 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. - [BPDA20-det Adversarial Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Clean Accuracy | Result date | Report paper | | --- | --- | --- | --- | | PurSAMERE | 91.18 | Not recorded | 69896a2bc97a0b3e3b5dc5dc | | DP\_DDIM with ADDT | 88.77 | Not recorded | 69896a2bc97a0b3e3b5dc5dc | | PurSAMERE | 88.45 | Not recorded | 69896a2bc97a0b3e3b5dc5dc | | DP\_DDIM | 88.38 | Not recorded | 69896a2bc97a0b3e3b5dc5dc | | DP\_DDPM | 85.94 | Not recorded | 69896a2bc97a0b3e3b5dc5dc | | PurSAMERE | 85.68 | Not recorded | 69896a2bc97a0b3e3b5dc5dc | | DP\_DDPM with ADDT | 85.64 | Not recorded | 69896a2bc97a0b3e3b5dc5dc | ### PurSAMERE Clean Accuracy: 91.18. Result ID: 6998e98a5698665ec44df6e4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"ϱ\_pur":"2"}. This record does not assert independent reproduction. ### DP\_DDIM with ADDT Clean Accuracy: 88.77. Result ID: 6998e98a5698665ec44df6ea. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Source":"Liu et al.","ADDT":"true"}. This record does not assert independent reproduction. ### PurSAMERE Clean Accuracy: 88.45. Result ID: 6998e98a5698665ec44df6e5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"ϱ\_pur":"2.5"}. This record does not assert independent reproduction. ### DP\_DDIM Clean Accuracy: 88.38. Result ID: 6998e98a5698665ec44df6e8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Source":"Liu et al.","ADDT":"false"}. This record does not assert independent reproduction. ### DP\_DDPM Clean Accuracy: 85.94. Result ID: 6998e98a5698665ec44df6e7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Source":"Liu et al.","ADDT":"false"}. This record does not assert independent reproduction. ### PurSAMERE Clean Accuracy: 85.68. Result ID: 6998e98a5698665ec44df6e6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"ϱ\_pur":"3"}. This record does not assert independent reproduction. ### DP\_DDPM with ADDT Clean Accuracy: 85.64. Result ID: 6998e98a5698665ec44df6e9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Source":"Liu et al.","ADDT":"true"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.