{"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/smoothmix-training-confidence-calibrated","title":"SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness","arxiv_id":"2111.09277","date":"2021-11-17","proceeding":"NeurIPS 2021 12","authors":["Jongheon Jeong","Sejun Park","Minkyu Kim","Heung-Chang Lee","DoGuk Kim","Jinwoo Shin"],"abstract":"Randomized smoothing is currently a state-of-the-art method to construct a certifiably robust classifier from neural networks against $\\ell_2$-adversarial perturbations. Under the paradigm, the robustness of a classifier is aligned with the prediction confidence, i.e., the higher confidence from a smoothed classifier implies the better robustness. This motivates us to rethink the fundamental trade-off between accuracy and robustness in terms of calibrating confidences of a smoothed classifier. In this paper, we propose a simple training scheme, coined SmoothMix, to control the robustness of smoothed classifiers via self-mixup: it trains on convex combinations of samples along the direction of adversarial perturbation for each input. The proposed procedure effectively identifies over-confident, near off-class samples as a cause of limited robustness in case of smoothed classifiers, and offers an intuitive way to adaptively set a new decision boundary between these samples for better robustness. Our experimental results demonstrate that the proposed method can significantly improve the certified $\\ell_2$-robustness of smoothed classifiers compared to existing state-of-the-art robust training methods.","url_abs":"https://arxiv.org/abs/2111.09277v1","url_pdf":"https://arxiv.org/pdf/2111.09277v1.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":"smoothmix-training-confidence-calibrated","repo_url":"https://github.com/jh-jeong/smoothmix","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2111.09277","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.09277"}},"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/jh-jeong/smoothmix","reach":null}],"summary":{"ran":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"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":"4d445e966929e029","entry":"SmoothAdv_PGD","repo":"jh-jeong/smoothmix","repo_kind":"official","path":"code/train_consistency.py","file_url":"https://github.com/jh-jeong/smoothmix/blob/HEAD/code/train_consistency.py","link_basis":"first_harvest_node","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":"4d445e966929e029"}},{"code_sha256_prefix":"dff4428e257e2940","entry":"Attacker","repo":"jh-jeong/smoothmix","repo_kind":"official","path":"code/train_consistency.py","file_url":"https://github.com/jh-jeong/smoothmix/blob/HEAD/code/train_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":"dff4428e257e2940"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}