{"id":20096574,"url":"https://github.com/hendrycks/natural-adv-examples","last_synced_at":"2025-04-04T21:10:20.403Z","repository":{"id":37405550,"uuid":"191111394","full_name":"hendrycks/natural-adv-examples","owner":"hendrycks","description":"A Harder ImageNet Test Set (CVPR 2021)","archived":false,"fork":false,"pushed_at":"2024-03-23T14:43:00.000Z","size":2202,"stargazers_count":602,"open_issues_count":7,"forks_count":52,"subscribers_count":11,"default_branch":"master","last_synced_at":"2025-03-28T20:09:42.319Z","etag":null,"topics":["adversarial-attacks","adversarial-example","domain-generalization","imagenet","ml-safety","robustness"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/hendrycks.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-06-10T06:37:37.000Z","updated_at":"2025-03-21T09:49:22.000Z","dependencies_parsed_at":"2024-12-14T03:06:49.377Z","dependency_job_id":"7ae0a22a-169e-4929-8f43-bdd5a9a30caf","html_url":"https://github.com/hendrycks/natural-adv-examples","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hendrycks%2Fnatural-adv-examples","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hendrycks%2Fnatural-adv-examples/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hendrycks%2Fnatural-adv-examples/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hendrycks%2Fnatural-adv-examples/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hendrycks","download_url":"https://codeload.github.com/hendrycks/natural-adv-examples/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247249532,"owners_count":20908212,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["adversarial-attacks","adversarial-example","domain-generalization","imagenet","ml-safety","robustness"],"created_at":"2024-11-13T16:59:15.548Z","updated_at":"2025-04-04T21:10:20.382Z","avatar_url":"https://github.com/hendrycks.png","language":"Python","funding_links":[],"categories":["Related Datasets Link","Datasets \u0026 Benchmarks"],"sub_categories":["**Other**","Robustness / Distribution Shift"],"readme":"# Natural Adversarial Examples\n\nWe introduce [natural adversarial examples](https://arxiv.org/abs/1907.07174) -- real-world, unmodified, and naturally occurring examples that cause machine learning model performance to significantly degrade.\n\n__[Download the natural adversarial example dataset ImageNet-A for image classifiers here](https://people.eecs.berkeley.edu/~hendrycks/imagenet-a.tar).__\n\n__[Download the natural adversarial example dataset ImageNet-O for out-of-distribution detectors here](https://people.eecs.berkeley.edu/~hendrycks/imagenet-o.tar).__\n\n\u003cimg align=\"center\" src=\"examples.png\" width=\"400\"\u003e\nNatural adversarial examples from ImageNet-A and ImageNet-O. The black text is the actual class, and\nthe red text is a ResNet-50 prediction and its confidence. ImageNet-A contains images that classifiers should be\nable to classify, while ImageNet-O contains anomalies of unforeseen classes which should result in low-confidence\npredictions. ImageNet-1K models do not train on examples from “Photosphere” nor “Verdigris” classes, so these images\nare anomalous. Many natural adversarial examples lead to wrong predictions, despite having no adversarial modifications as they are examples which occur naturally.\n\n## Citation\n\nIf you find this useful in your research, please consider citing:\n\n    @article{hendrycks2021nae,\n      title={Natural Adversarial Examples},\n      author={Dan Hendrycks and Kevin Zhao and Steven Basart and Jacob Steinhardt and Dawn Song},\n      journal={CVPR},\n      year={2021}\n    }\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhendrycks%2Fnatural-adv-examples","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhendrycks%2Fnatural-adv-examples","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhendrycks%2Fnatural-adv-examples/lists"}