{"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/multi-scale-diffusion-denoised-smoothing-1","title":"Multi-scale Diffusion Denoised Smoothing","arxiv_id":"2310.16779","date":"2023-10-25","proceeding":"NeurIPS 2023 11","authors":["Jongheon Jeong","Jinwoo Shin"],"abstract":"Along with recent diffusion models, randomized smoothing has become one of a few tangible approaches that offers adversarial robustness to models at scale, e.g., those of large pre-trained models. Specifically, one can perform randomized smoothing on any classifier via a simple \"denoise-and-classify\" pipeline, so-called denoised smoothing, given that an accurate denoiser is available - such as diffusion model. In this paper, we present scalable methods to address the current trade-off between certified robustness and accuracy in denoised smoothing. Our key idea is to \"selectively\" apply smoothing among multiple noise scales, coined multi-scale smoothing, which can be efficiently implemented with a single diffusion model. This approach also suggests a new objective to compare the collective robustness of multi-scale smoothed classifiers, and questions which representation of diffusion model would maximize the objective. To address this, we propose to further fine-tune diffusion model (a) to perform consistent denoising whenever the original image is recoverable, but (b) to generate rather diverse outputs otherwise. Our experiments show that the proposed multi-scale smoothing scheme combined with diffusion fine-tuning enables strong certified robustness available with high noise level while maintaining its accuracy close to non-smoothed classifiers.","url_abs":"https://arxiv.org/abs/2310.16779v3","url_pdf":"https://arxiv.org/pdf/2310.16779v3.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":"multi-scale-diffusion-denoised-smoothing-1","repo_url":"https://github.com/jh-jeong/smoothing-multiscale","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"},{"task_slug":"denoising","task_name":"Denoising"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"randomized-smoothing","method_name":"Randomized Smoothing"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.16779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.16779"}},"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/modestyachts/CIFAR-10.1","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/jh-jeong/smoothing-multiscale","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"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":"dd41358588f96a01","entry":"DDPM","repo":"jh-jeong/smoothing-multiscale","repo_kind":"official","path":"predict_mdds.py","file_url":"https://github.com/jh-jeong/smoothing-multiscale/blob/HEAD/predict_mdds.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":"dd41358588f96a01"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}