{"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/improving-robustness-using-generated-data","title":"Improving Robustness using Generated Data","arxiv_id":"2110.09468","date":"2021-10-18","proceeding":"NeurIPS 2021 12","authors":["Sven Gowal","Sylvestre-Alvise Rebuffi","Olivia Wiles","Florian Stimberg","Dan Andrei Calian","Timothy Mann"],"abstract":"Recent work argues that robust training requires substantially larger datasets than those required for standard classification. On CIFAR-10 and CIFAR-100, this translates into a sizable robust-accuracy gap between models trained solely on data from the original training set and those trained with additional data extracted from the \"80 Million Tiny Images\" dataset (TI-80M). In this paper, we explore how generative models trained solely on the original training set can be leveraged to artificially increase the size of the original training set and improve adversarial robustness to $\\ell_p$ norm-bounded perturbations. We identify the sufficient conditions under which incorporating additional generated data can improve robustness, and demonstrate that it is possible to significantly reduce the robust-accuracy gap to models trained with additional real data. Surprisingly, we even show that even the addition of non-realistic random data (generated by Gaussian sampling) can improve robustness. We evaluate our approach on CIFAR-10, CIFAR-100, SVHN and TinyImageNet against $\\ell_\\infty$ and $\\ell_2$ norm-bounded perturbations of size $\\epsilon = 8/255$ and $\\epsilon = 128/255$, respectively. We show large absolute improvements in robust accuracy compared to previous state-of-the-art methods. Against $\\ell_\\infty$ norm-bounded perturbations of size $\\epsilon = 8/255$, our models achieve 66.10% and 33.49% robust accuracy on CIFAR-10 and CIFAR-100, respectively (improving upon the state-of-the-art by +8.96% and +3.29%). Against $\\ell_2$ norm-bounded perturbations of size $\\epsilon = 128/255$, our model achieves 78.31% on CIFAR-10 (+3.81%). These results beat most prior works that use external data.","url_abs":"https://arxiv.org/abs/2110.09468v2","url_pdf":"https://arxiv.org/pdf/2110.09468v2.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":"improving-robustness-using-generated-data","repo_url":"https://github.com/imrahulr/adversarial_robustness_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.09468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.09468"}},"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":"deterministic:regex_extraction","url":"https://github.com/fra31/auto-attack","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/deepmind/deepmind-research","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/imrahulr/adversarial_robustness_pytorch","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran":5,"unverified":1},"by_repo_kind":{"listed":{"samples":7,"ran":6,"repositories":1}},"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":0,"samples":[{"code_sha256_prefix":"9aa516330b945a07","entry":"accuracy","repo":"imrahulr/adversarial_robustness_pytorch","repo_kind":"listed","path":"core/metrics.py","file_url":"https://github.com/imrahulr/adversarial_robustness_pytorch/blob/HEAD/core/metrics.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9aa516330b945a07"}},{"code_sha256_prefix":"6d57c3097e379953","entry":"calc_l2distsq","repo":"imrahulr/adversarial_robustness_pytorch","repo_kind":"listed","path":"core/attacks/utils.py","file_url":"https://github.com/imrahulr/adversarial_robustness_pytorch/blob/HEAD/core/attacks/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6d57c3097e379953"}},{"code_sha256_prefix":"8a6e2e06ca96fb3c","entry":"perturb_deepfool","repo":"imrahulr/adversarial_robustness_pytorch","repo_kind":"listed","path":"core/attacks/deepfool.py","file_url":"https://github.com/imrahulr/adversarial_robustness_pytorch/blob/HEAD/core/attacks/deepfool.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8a6e2e06ca96fb3c"}},{"code_sha256_prefix":"a99efdab28da25d8","entry":"preact_resnet","repo":"imrahulr/adversarial_robustness_pytorch","repo_kind":"listed","path":"core/models/preact_resnet.py","file_url":"https://github.com/imrahulr/adversarial_robustness_pytorch/blob/HEAD/core/models/preact_resnet.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a99efdab28da25d8"}},{"code_sha256_prefix":"096e065144e00e11","entry":"replicate_input","repo":"imrahulr/adversarial_robustness_pytorch","repo_kind":"listed","path":"core/attacks/utils.py","file_url":"https://github.com/imrahulr/adversarial_robustness_pytorch/blob/HEAD/core/attacks/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"096e065144e00e11"}},{"code_sha256_prefix":"706e45721616b050","entry":"replicate_input_withgrad","repo":"imrahulr/adversarial_robustness_pytorch","repo_kind":"listed","path":"core/attacks/utils.py","file_url":"https://github.com/imrahulr/adversarial_robustness_pytorch/blob/HEAD/core/attacks/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"706e45721616b050"}},{"code_sha256_prefix":"ec5326fd666c5823","entry":"perturb_iterative","repo":"imrahulr/adversarial_robustness_pytorch","repo_kind":"listed","path":"core/attacks/pgd.py","file_url":"https://github.com/imrahulr/adversarial_robustness_pytorch/blob/HEAD/core/attacks/pgd.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ec5326fd666c5823"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}