Methods › General › Robustness Methods › Denoised Smoothing
Denoised Smoothing
Introduced by Hadi Salman et al. in Denoised Smoothing: A Provable Defense for Pretrained Classifiers
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Denoised Smoothing is a method for obtaining a provably robust classifier from a fixed pretrained one, without any additional training or fine-tuning of the latter. The basic idea is to prepend a custom-trained denoiser before the pretrained classifier, and then apply randomized smoothing. Randomized smoothing is a certified defense that converts any given classifier f into a new smoothed classifier g that is characterized by a non-linear Lipschitz property. When queried at a point x, the smoothed classifier g outputs the class that is most likely to be returned by f under isotropic Gaussian perturbations of its inputs. Unfortunately, randomized smoothing requires that the underlying classifier f is robust to relatively large random Gaussian perturbations of the input, which is not the case for off-the-shelf pretrained models. By applying our custom-trained denoiser to the classifier f, we can effectively make f robust to such Gaussian perturbations, thereby making it “suitable” for randomized smoothing.
In Syntology harvested code stored, below machine verification (unverified_code; harvested), served level V1; retrieve with get_harvested_code_for_paper(arxiv_id='2003.01908'). Repositories: 4 listed of 4 in the graph, strongest link: official. The lookup matched a paper by its title, arXiv:2003.01908, not a method entry. This answer is about arXiv:2003.01908, the paper the archive credits with this method.
Origin paper of this answer, arXiv:2003.01908 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 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 (of 4 harvested samples) · 1 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 8 · with a code link: 6 · where Syntology ran a sample: 4 (4 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (4 of 8 tagged: 4 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 8 of 8, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Beyond Classification: Evaluating Diffusion Denoised Smoothing for Security-Utility Trade off 21 May 2025 · 0 repositories · arXiv:2505.15594
-
Confidence-aware Denoised Fine-tuning of Off-the-shelf Models for Certified Robustness 13 Nov 2024 · 1 repository · arXiv:2411.08933
-
Advancing the Robustness of Large Language Models through Self-Denoised Smoothing 18 Apr 2024 · 1 repository · arXiv:2404.12274Syntology official (archive's flag): 4 ran · 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 (of 4 harvested samples) · 4 pointer-only (licence)
-
Certified Zeroth-order Black-Box Defense with Robust UNet Denoiser 13 Apr 2023 · 0 repositories · arXiv:2304.06430
-
(Certified!!) Adversarial Robustness for Free! 21 Jun 2022 · 3 repositories · arXiv:2206.10550Syntology official (archive's flag): 12 ran · 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 (of 34 harvested samples) · 13 pointer-only (licence)
-
How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective 27 Mar 2022 · 1 repository · arXiv:2203.14195Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)
-
Poisoned classifiers are not only backdoored, they are fundamentally broken 18 Oct 2020 · 1 repository · arXiv:2010.09080Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples)
-
Denoised Smoothing: A Provable Defense for Pretrained Classifiers 4 Mar 2020 · 4 repositories · arXiv:2003.01908Syntology official (archive's flag): 1 ran · 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 (of 4 harvested samples) · 1 pointer-only (licence)
Tasks archive 2025-07-28
9 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Adversarial Robustness | 4 |
| Denoising | 3 |
| Image Classification | 2 |
| Image Reconstruction | 2 |
| image-classification | 2 |
| Adversarial Attack | 1 |
| General Classification | 1 |
| Hallucination | 1 |
| Robust classification | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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