Papers › Certified Adversarial Robustness via Randomized Smoothing

Certified Adversarial Robustness via Randomized Smoothing

8 Feb 2019arXiv:1902.02918archive 2025-07-28

Jeremy M Cohen, Elan Rosenfeld, J. Zico Kolter

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 ℓ₂ norm. This "randomized smoothing" technique has been proposed recently in the literature, but existing guarantees are loose. We prove a tight robustness guarantee in ℓ₂ 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 ℓ₂ 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 ℓ₂ 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.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

locuslab/smoothing officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
RaphaelOlivier/gard_eval2_public mentioned on GitHubpytorchSyntology: not harvested report
akshaymehra24/poisoning_certified_defenses mentioned on GitHubtfSyntology: not harvested report
alevine0/smoothingGenGaussian mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
aounon/distributional-robustness mentioned on GitHubpytorchSyntology: not harvested report
blaisedelattre/bridging_the_gap_rs mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to (Certified!!) Adversarial Robustness for Free! (arXiv:2206.10550; that paper's own run record: 28 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 4 honoured, 0 violated, 11 with no contract checked; 13 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
jayjaynandy/RBF-CNN mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Approximate Manifold Defense Against Multiple Adversarial Perturbations (arXiv:2004.02183; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
llylly/dsrs mentioned on GitHubpytorchBSD-3-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Double Sampling Randomized Smoothing (arXiv:2206.07912; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 14 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
mwojnars/nifty mentioned on GitHubtfGPL-3.0Syntology: not harvested report
sayakpaul/Denoised-Smoothing-TF mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Denoised Smoothing: A Provable Defense for Pretrained Classifiers (arXiv:2003.01908; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
xzh0u/randomized-smoothing mentioned on GitHubpytorchSyntology: not harvested report
zijianh4/CROP-leaderboard.github.io mentioned on GitHubSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Adversarial DefenseAdversarial RobustnessRobust classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: Randomized Smoothing

Randomized Smoothing

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections