{"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/adversarially-robust-classifier-with","title":"Towards Bridging the gap between Empirical and Certified Robustness against Adversarial Examples","arxiv_id":"2102.05096","date":"2021-02-09","proceeding":null,"authors":["Jay Nandy","Sudipan Saha","Wynne Hsu","Mong Li Lee","Xiao Xiang Zhu"],"abstract":"The current state-of-the-art defense methods against adversarial examples typically focus on improving either empirical or certified robustness. Among them, adversarially trained (AT) models produce empirical state-of-the-art defense against adversarial examples without providing any robustness guarantees for large classifiers or higher-dimensional inputs. In contrast, existing randomized smoothing based models achieve state-of-the-art certified robustness while significantly degrading the empirical robustness against adversarial examples. In this paper, we propose a novel method, called \\emph{Certification through Adaptation}, that transforms an AT model into a randomized smoothing classifier during inference to provide certified robustness for $\\ell_2$ norm without affecting their empirical robustness against adversarial attacks. We also propose \\emph{Auto-Noise} technique that efficiently approximates the appropriate noise levels to flexibly certify the test examples using randomized smoothing technique. Our proposed \\emph{Certification through Adaptation} with \\emph{Auto-Noise} technique achieves an \\textit{average certified radius (ACR) scores} up to $1.102$ and $1.148$ respectively for CIFAR-10 and ImageNet datasets using AT models without affecting their empirical robustness or benign accuracy. Therefore, our paper is a step towards bridging the gap between the empirical and certified robustness against adversarial examples by achieving both using the same classifier.","url_abs":"https://arxiv.org/abs/2102.05096v3","url_pdf":"https://arxiv.org/pdf/2102.05096v3.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":[],"tasks":[{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"randomized-smoothing","method_name":"Randomized Smoothing"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2102.05096","atlas_url":"https://app.syntology.ai/?focus=2102.05096","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.05096"}},"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":"deterministic:regex_extraction","url":"https://github.com/Hadisalman/smoothing-adversarial","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"found_in_text":{"samples":3,"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":1,"samples":[{"code_sha256_prefix":"70a18435a0e20450","entry":"get_minibatches","repo":"Hadisalman/smoothing-adversarial","repo_kind":"found_in_text","path":"code/train_pgd.py","file_url":"https://github.com/Hadisalman/smoothing-adversarial/blob/HEAD/code/train_pgd.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"70a18435a0e20450"}},{"code_sha256_prefix":"156c1e3dc785672c","entry":"Attacker","repo":"Hadisalman/smoothing-adversarial","repo_kind":"found_in_text","path":"code/train_pgd.py","file_url":"https://github.com/Hadisalman/smoothing-adversarial/blob/HEAD/code/train_pgd.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":"156c1e3dc785672c"}},{"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":"44eff0215f284676","entry":"train","repo":"Hadisalman/smoothing-adversarial","repo_kind":"found_in_text","path":"code/train_pgd.py","file_url":"https://github.com/Hadisalman/smoothing-adversarial/blob/HEAD/code/train_pgd.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":"44eff0215f284676"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}