{"task":"Adversarial Robustness","dataset":"CIFAR-10","metric_names":["Accuracy","Robust Accuracy","Attack: AutoAttack"],"rows":[{"id":759049,"task":"Adversarial Robustness","parent_task":null,"dataset":"CIFAR-10","model_name":"A Geometric Probe of the Accuracy-Robust","metrics":{"Accuracy":"95.63"},"paper_url":"https://paperswithcode.com/paper/a-geometric-probe-of-the-accuracy-robustness-trade-off-sharp-boundaries-in-symmetry-breaking-dimensional-expansion","paper_title":"A Geometric Probe of the Accuracy-Robustness Trade-off: Sharp Boundaries in Symmetry-Breaking Dimensional Expansion","paper_date":"2026-02-20","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]},{"id":120665,"task":"Adversarial Robustness","parent_task":null,"dataset":"CIFAR-10","model_name":"Mixed classifier","metrics":{"Accuracy":"95.23","Attack: AutoAttack":"68.06","Robust Accuracy":"68.06"},"paper_url":"https://arxiv.org/abs/2301.12554v5","paper_title":"Improving the Accuracy-Robustness Trade-Off of Classifiers via Adaptive Smoothing","paper_date":"2023-01-29","code_links":[{"title":"codelion/adaptive-classifier","url":"https://github.com/codelion/adaptive-classifier"},{"title":"bai-yt/adaptivesmoothing","url":"https://github.com/bai-yt/adaptivesmoothing"}],"metrics_order":"[\"Accuracy\", \"Robust Accuracy\", \"Attack: AutoAttack\"]","area":"Adversarial","uses_additional_data":1,"source":"archive","tags":[]},{"id":759412,"task":"Adversarial Robustness","parent_task":null,"dataset":"CIFAR-10","model_name":"Neural Architecture Search with Mixed Bi","metrics":{"Accuracy":"95.16"},"paper_url":"https://paperswithcode.com/paper/neural-architecture-search-with-mixed-bio-inspired-learning-rules","paper_title":"Neural Architecture Search with Mixed Bio-inspired Learning Rules","paper_date":"2025-07-17","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]},{"id":120666,"task":"Adversarial Robustness","parent_task":null,"dataset":"CIFAR-10","model_name":"Stochastic-LWTA/PGD/WideResNet-34-10","metrics":{"Accuracy":"92.26","Attack: AutoAttack":"82.6","Robust Accuracy":"84.3"},"paper_url":"https://arxiv.org/abs/2112.02671v1","paper_title":"Stochastic Local Winner-Takes-All Networks Enable Profound Adversarial Robustness","paper_date":"2021-12-05","code_links":[{"title":"konpanousis/adversarial-lwta-autoattack","url":"https://github.com/konpanousis/adversarial-lwta-autoattack"}],"metrics_order":"[\"Accuracy\", \"Robust Accuracy\", \"Attack: AutoAttack\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":120667,"task":"Adversarial Robustness","parent_task":null,"dataset":"CIFAR-10","model_name":"Stochastic-LWTA/PGD/WideResNet-34-5","metrics":{"Accuracy":"91.88","Attack: AutoAttack":"81.22","Robust Accuracy":"83.4"},"paper_url":"https://arxiv.org/abs/2112.02671v1","paper_title":"Stochastic Local Winner-Takes-All Networks Enable Profound Adversarial Robustness","paper_date":"2021-12-05","code_links":[{"title":"konpanousis/adversarial-lwta-autoattack","url":"https://github.com/konpanousis/adversarial-lwta-autoattack"}],"metrics_order":"[\"Accuracy\", \"Robust Accuracy\", \"Attack: AutoAttack\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":120668,"task":"Adversarial Robustness","parent_task":null,"dataset":"CIFAR-10","model_name":"GLOT-DR","metrics":{"Accuracy":"84.13","Attack: AutoAttack":"49.94"},"paper_url":"https://arxiv.org/abs/2203.00553v3","paper_title":"Global-Local Regularization Via Distributional Robustness","paper_date":"2022-03-01","code_links":[{"title":"viethoang1512/glot","url":"https://github.com/viethoang1512/glot"}],"metrics_order":"[\"Accuracy\", \"Robust Accuracy\", \"Attack: AutoAttack\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":120669,"task":"Adversarial Robustness","parent_task":null,"dataset":"CIFAR-10","model_name":"TRADES-ANCRA/ResNet18","metrics":{"Accuracy":"81.70","Attack: AutoAttack":"59.70"},"paper_url":"https://arxiv.org/abs/2310.03358v2","paper_title":"Enhancing Robust Representation in Adversarial Training: Alignment and Exclusion Criteria","paper_date":"2023-10-05","code_links":[{"title":"changzhang777/ancra","url":"https://github.com/changzhang777/ancra"}],"metrics_order":"[\"Accuracy\", \"Robust Accuracy\", \"Attack: AutoAttack\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]}]}