# Certified Image Classification on ImageNet (Epsilon 1.0, 2.0) Source: [Certified Image Classification on ImageNet (Epsilon 1.0, 2.0)]() Collection index: [llms.txt]() Data updated: 2026-05-26T10:49:46.940Z Evaluation of Image Classification performance on the standard ImageNet dataset, specifically reporting Certified Accuracy under adversarial perturbation bounds (epsilon=1.0 and epsilon=2.0). 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) | ImageNet | | Metric | Certified Accuracy (Epsilon 1.0) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 6 of 6 | | 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 - [Certified Accuracy (Epsilon 1.0)](): Higher is better; unit: PERCENT. - [Certified Accuracy (Epsilon 2.0)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Certified Accuracy (Epsilon 1.0) | Result date | Report paper | | --- | --- | --- | --- | | DensePure | 67 | Not recorded | 6a152965dbd7150506f7e325 | | Denoising with Pre-trained Diffusion Models | 54.3 | Not recorded | 6a152965dbd7150506f7e325 | | GENELLIPS | 45.7 | Not recorded | 6a152965dbd7150506f7e325 | | Randomized Smoothing and Adversarial Training | 45 | Not recorded | 6a152965dbd7150506f7e325 | | Ensemble Models and Variance Reduction | 44.6 | Not recorded | 6a152965dbd7150506f7e325 | | Ensemble Models | 44.4 | Not recorded | 6a152965dbd7150506f7e325 | ### DensePure Certified Accuracy (Epsilon 1.0): 67. Result ID: 6a157ac9fbc373592c0dae62. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Denoising with Pre-trained Diffusion Models Certified Accuracy (Epsilon 1.0): 54.3. Result ID: 6a157ac9fbc373592c0dae63. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GENELLIPS Certified Accuracy (Epsilon 1.0): 45.7. Result ID: 6a157ac9fbc373592c0dae67. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Randomized Smoothing and Adversarial Training Certified Accuracy (Epsilon 1.0): 45. Result ID: 6a157ac9fbc373592c0dae64. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Ensemble Models and Variance Reduction Certified Accuracy (Epsilon 1.0): 44.6. Result ID: 6a157ac9fbc373592c0dae65. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Ensemble Models Certified Accuracy (Epsilon 1.0): 44.4. Result ID: 6a157ac9fbc373592c0dae66. [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.