{"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/certified-adversarial-robustness-via","title":"Certified Adversarial Robustness via Randomized Smoothing","arxiv_id":"1902.02918","date":"2019-02-08","proceeding":null,"authors":["Jeremy M Cohen","Elan Rosenfeld","J. Zico Kolter"],"abstract":"We show how to turn any classifier that classifies well under Gaussian noise into a new classifier that is certifiably robust to adversarial perturbations under the $\\ell_2$ norm. This \"randomized smoothing\" technique has been proposed recently in the literature, but existing guarantees are loose. We prove a tight robustness guarantee in $\\ell_2$ norm for smoothing with Gaussian noise. We use randomized smoothing to obtain an ImageNet classifier with e.g. a certified top-1 accuracy of 49% under adversarial perturbations with $\\ell_2$ norm less than 0.5 (=127/255). No certified defense has been shown feasible on ImageNet except for smoothing. On smaller-scale datasets where competing approaches to certified $\\ell_2$ robustness are viable, smoothing delivers higher certified accuracies. Our strong empirical results suggest that randomized smoothing is a promising direction for future research into adversarially robust classification. Code and models are available at http://github.com/locuslab/smoothing.","url_abs":"https://arxiv.org/abs/1902.02918v2","url_pdf":"https://arxiv.org/pdf/1902.02918v2.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":"certified-adversarial-robustness-via","repo_url":"https://github.com/locuslab/smoothing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"certified-adversarial-robustness-via","repo_url":"https://github.com/RaphaelOlivier/gard_eval2_public","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"certified-adversarial-robustness-via","repo_url":"https://github.com/akshaymehra24/poisoning_certified_defenses","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"certified-adversarial-robustness-via","repo_url":"https://github.com/alevine0/smoothingGenGaussian","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"certified-adversarial-robustness-via","repo_url":"https://github.com/aounon/distributional-robustness","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"certified-adversarial-robustness-via","repo_url":"https://github.com/blaisedelattre/bridging_the_gap_rs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"certified-adversarial-robustness-via","repo_url":"https://github.com/jayjaynandy/RBF-CNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"certified-adversarial-robustness-via","repo_url":"https://github.com/llylly/dsrs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"certified-adversarial-robustness-via","repo_url":"https://github.com/mwojnars/nifty","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"certified-adversarial-robustness-via","repo_url":"https://github.com/sayakpaul/Denoised-Smoothing-TF","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"certified-adversarial-robustness-via","repo_url":"https://github.com/xzh0u/randomized-smoothing","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"certified-adversarial-robustness-via","repo_url":"https://github.com/zijianh4/CROP-leaderboard.github.io","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"adversarial-defense","task_name":"Adversarial Defense"},{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"},{"task_slug":"robust-classification","task_name":"Robust classification"}],"methods":[{"method_slug":"randomized-smoothing","method_name":"Randomized Smoothing"}],"datasets_introduced":[],"methods_introduced":[{"slug":"randomized-smoothing","name":"Randomized Smoothing","full_name":"Randomized Smoothing"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.02918","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}