{"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/consistency-regularization-for-certified","title":"Consistency Regularization for Certified Robustness of Smoothed Classifiers","arxiv_id":"2006.04062","date":"2020-06-07","proceeding":"NeurIPS 2020 12","authors":["Jongheon Jeong","Jinwoo Shin"],"abstract":"A recent technique of randomized smoothing has shown that the worst-case (adversarial) $\\ell_2$-robustness can be transformed into the average-case Gaussian-robustness by \"smoothing\" a classifier, i.e., by considering the averaged prediction over Gaussian noise. In this paradigm, one should rethink the notion of adversarial robustness in terms of generalization ability of a classifier under noisy observations. We found that the trade-off between accuracy and certified robustness of smoothed classifiers can be greatly controlled by simply regularizing the prediction consistency over noise. This relationship allows us to design a robust training objective without approximating a non-existing smoothed classifier, e.g., via soft smoothing. Our experiments under various deep neural network architectures and datasets show that the \"certified\" $\\ell_2$-robustness can be dramatically improved with the proposed regularization, even achieving better or comparable results to the state-of-the-art approaches with significantly less training costs and hyperparameters.","url_abs":"https://arxiv.org/abs/2006.04062v4","url_pdf":"https://arxiv.org/pdf/2006.04062v4.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":"consistency-regularization-for-certified","repo_url":"https://github.com/jh-jeong/smoothing-consistency","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"}],"methods":[{"method_slug":"randomized-smoothing","method_name":"Randomized Smoothing"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.04062","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.04062"}},"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/jh-jeong/smoothing-consistency","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran":1,"unverified":4},"by_repo_kind":{"official":{"samples":6,"ran":2,"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":"fac5364e2f53c6db","entry":"conv3x3","repo":"jh-jeong/smoothing-consistency","repo_kind":"official","path":"code/archs/cifar_resnet.py","file_url":"https://github.com/jh-jeong/smoothing-consistency/blob/HEAD/code/archs/cifar_resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"23f822c3d6d64a12","entry":"entropy","repo":"jh-jeong/smoothing-consistency","repo_kind":"official","path":"code/consistency.py","file_url":"https://github.com/jh-jeong/smoothing-consistency/blob/HEAD/code/consistency.py","link_basis":"plan_row","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":"23f822c3d6d64a12"}},{"code_sha256_prefix":"3d45147f0a674bc0","entry":"consistency_loss","repo":"jh-jeong/smoothing-consistency","repo_kind":"official","path":"code/consistency.py","file_url":"https://github.com/jh-jeong/smoothing-consistency/blob/HEAD/code/consistency.py","link_basis":"first_harvest_node","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":"3d45147f0a674bc0"}},{"code_sha256_prefix":"009cb123eeb4af07","entry":"get_dataset","repo":"jh-jeong/smoothing-consistency","repo_kind":"official","path":"code/datasets.py","file_url":"https://github.com/jh-jeong/smoothing-consistency/blob/HEAD/code/datasets.py","link_basis":"first_harvest_node","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":"009cb123eeb4af07"}},{"code_sha256_prefix":"626fd2d46f9e5106","entry":"get_num_classes","repo":"jh-jeong/smoothing-consistency","repo_kind":"official","path":"code/datasets.py","file_url":"https://github.com/jh-jeong/smoothing-consistency/blob/HEAD/code/datasets.py","link_basis":"first_harvest_node","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":"626fd2d46f9e5106"}},{"code_sha256_prefix":"6518bcfd499a3632","entry":"kl_div","repo":"jh-jeong/smoothing-consistency","repo_kind":"official","path":"code/consistency.py","file_url":"https://github.com/jh-jeong/smoothing-consistency/blob/HEAD/code/consistency.py","link_basis":"first_harvest_node","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":"6518bcfd499a3632"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}