# Adversarial Image Classification on ImageNet (Linf eps=4/255, test) Source: [Adversarial Image Classification on ImageNet (Linf eps=4/255, test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:28:05.266Z Evaluation of Image Classification robustness on the test split of ImageNet under L-infinity adversarial constraints (epsilon=4/255), reporting standard accuracy and robustness metrics against PGD attacks. 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 Linf epsilon=4/255 (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 4 of 4 | | 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. - [Robust Accuracy (PGD-10)](): Higher is better; unit: PERCENT. - [Robust Accuracy (PGD-50)](): Higher is better; unit: PERCENT. - [Robust Accuracy (PGD-100)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | MixACM + RA | 62.05 | Not recorded | 68fa6b361e209131cea2cf0b | | Free-AT | 60.21 | Not recorded | 68fa6b361e209131cea2cf0b | | MixACM | 59.64 | Not recorded | 68fa6b361e209131cea2cf0b | | Fast-AT | 55.45 | Not recorded | 68fa6b361e209131cea2cf0b | ### MixACM + RA Accuracy: 62.05. Result ID: 698e7150ffc3901de09da2b2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Train ε":"0"}. This record does not assert independent reproduction. ### Free-AT Accuracy: 60.21. Result ID: 698e7150ffc3901de09da2af. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Train ε":"4/255"}. This record does not assert independent reproduction. ### MixACM Accuracy: 59.64. Result ID: 698e7150ffc3901de09da2b1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Train ε":"0"}. This record does not assert independent reproduction. ### Fast-AT Accuracy: 55.45. Result ID: 698e7150ffc3901de09da2b0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Train ε":"4/255"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.