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.
Papers archive 2025-07-28
8 shown of 8, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
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 ran 4 of 4 samples · 0 unverified · 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 ran 14 of 34 samples · 20 unverified
-
How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective 27 Mar 2022 · 1 repository · arXiv:2203.14195Syntology ran 0 of 1 samples · 1 unverified
-
Poisoned classifiers are not only backdoored, they are fundamentally broken 18 Oct 2020 · 1 repository · arXiv:2010.09080Syntology ran 2 of 6 samples · 4 unverified
-
Denoised Smoothing: A Provable Defense for Pretrained Classifiers 4 Mar 2020 · 4 repositories · arXiv:2003.01908Syntology ran 1 of 4 samples · 3 unverified
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