{"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/confidence-aware-training-of-smoothed-1","title":"Confidence-aware Training of Smoothed Classifiers for Certified Robustness","arxiv_id":"2212.09000","date":"2022-12-18","proceeding":null,"authors":["Jongheon Jeong","Seojin Kim","Jinwoo Shin"],"abstract":"Any classifier can be \"smoothed out\" under Gaussian noise to build a new classifier that is provably robust to $\\ell_2$-adversarial perturbations, viz., by averaging its predictions over the noise via randomized smoothing. Under the smoothed classifiers, the fundamental trade-off between accuracy and (adversarial) robustness has been well evidenced in the literature: i.e., increasing the robustness of a classifier for an input can be at the expense of decreased accuracy for some other inputs. In this paper, we propose a simple training method leveraging this trade-off to obtain robust smoothed classifiers, in particular, through a sample-wise control of robustness over the training samples. We make this control feasible by using \"accuracy under Gaussian noise\" as an easy-to-compute proxy of adversarial robustness for an input. Specifically, we differentiate the training objective depending on this proxy to filter out samples that are unlikely to benefit from the worst-case (adversarial) objective. Our experiments show that the proposed method, despite its simplicity, consistently exhibits improved certified robustness upon state-of-the-art training methods. Somewhat surprisingly, we find these improvements persist even for other notions of robustness, e.g., to various types of common corruptions.","url_abs":"https://arxiv.org/abs/2212.09000v2","url_pdf":"https://arxiv.org/pdf/2212.09000v2.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":"confidence-aware-training-of-smoothed-1","repo_url":"https://github.com/alinlab/smoothing-catrs","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":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2212.09000","atlas_url":"https://app.syntology.ai/?focus=2212.09000","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.09000"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/alinlab/smoothing-catrs","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":6,"ran":4,"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":"3d45147f0a674bc0","entry":"consistency_loss","repo":"alinlab/smoothing-catrs","repo_kind":"official","path":"code/consistency.py","file_url":"https://github.com/alinlab/smoothing-catrs/blob/HEAD/code/consistency.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":"3d45147f0a674bc0"}},{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"alinlab/smoothing-catrs","repo_kind":"official","path":"code/archs/cifar_resnet.py","file_url":"https://github.com/alinlab/smoothing-catrs/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":"alinlab/smoothing-catrs","repo_kind":"official","path":"code/consistency.py","file_url":"https://github.com/alinlab/smoothing-catrs/blob/HEAD/code/consistency.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":"23f822c3d6d64a12"}},{"code_sha256_prefix":"ddca6b8fb149d7f9","entry":"get_num_classes","repo":"alinlab/smoothing-catrs","repo_kind":"official","path":"code/datasets.py","file_url":"https://github.com/alinlab/smoothing-catrs/blob/HEAD/code/datasets.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":"ddca6b8fb149d7f9"}},{"code_sha256_prefix":"8a021efe12dc7d06","entry":"get_dataset","repo":"alinlab/smoothing-catrs","repo_kind":"official","path":"code/datasets.py","file_url":"https://github.com/alinlab/smoothing-catrs/blob/HEAD/code/datasets.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":"8a021efe12dc7d06"}},{"code_sha256_prefix":"6518bcfd499a3632","entry":"kl_div","repo":"alinlab/smoothing-catrs","repo_kind":"official","path":"code/consistency.py","file_url":"https://github.com/alinlab/smoothing-catrs/blob/HEAD/code/consistency.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":"6518bcfd499a3632"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}