{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/adversarial-machine-learning-at-scale","title":"Adversarial Machine Learning at Scale","arxiv_id":"1611.01236","date":"2016-11-04","proceeding":null,"authors":["Alexey Kurakin","Ian Goodfellow","Samy Bengio"],"abstract":"Adversarial examples are malicious inputs designed to fool machine learning\nmodels. They often transfer from one model to another, allowing attackers to\nmount black box attacks without knowledge of the target model's parameters.\nAdversarial training is the process of explicitly training a model on\nadversarial examples, in order to make it more robust to attack or to reduce\nits test error on clean inputs. So far, adversarial training has primarily been\napplied to small problems. In this research, we apply adversarial training to\nImageNet. Our contributions include: (1) recommendations for how to succesfully\nscale adversarial training to large models and datasets, (2) the observation\nthat adversarial training confers robustness to single-step attack methods, (3)\nthe finding that multi-step attack methods are somewhat less transferable than\nsingle-step attack methods, so single-step attacks are the best for mounting\nblack-box attacks, and (4) resolution of a \"label leaking\" effect that causes\nadversarially trained models to perform better on adversarial examples than on\nclean examples, because the adversarial example construction process uses the\ntrue label and the model can learn to exploit regularities in the construction\nprocess.","url_abs":"http://arxiv.org/abs/1611.01236v2","url_pdf":"http://arxiv.org/pdf/1611.01236v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"adversarial-machine-learning-at-scale","repo_url":"https://github.com/JZ-LIANG/Ensemble-Adversarial-Training","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"adversarial-machine-learning-at-scale","repo_url":"https://github.com/cs-giung/course-dl-TP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"adversarial-machine-learning-at-scale","repo_url":"https://github.com/dennis-sell/pytorch-fun","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"adversarial-machine-learning-at-scale","repo_url":"https://github.com/facebookresearch/adversarial_image_defenses","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"adversarial-machine-learning-at-scale","repo_url":"https://github.com/gauthiercler/adversarial-mnist","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"adversarial-machine-learning-at-scale","repo_url":"https://github.com/tensorflow/models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"adversarial-machine-learning-at-scale","repo_url":"https://github.com/tensorflow/models/tree/master/research/adv_imagenet_models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.01236","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.01236"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tensorflow/models","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dennis-sell/pytorch-fun","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JZ-LIANG/Ensemble-Adversarial-Training","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gauthiercler/adversarial-mnist","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tensorflow/models/tree/master/research/adv_imagenet_models","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/adversarial_image_defenses","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cs-giung/course-dl-TP","reach":{"status":"unanswered"}}],"summary":{"unverified":2},"by_repo_kind":{},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"913d82af53065418","entry":"accuracy","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"913d82af53065418"}},{"code_sha256_prefix":"153a81cace8b8376","entry":"validate","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"153a81cace8b8376"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}