Papers › Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing

Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing

15 Apr 2024arXiv:2404.09586archive 2025-07-28

Song Xia, Yi Yu, Xudong Jiang, Henghui Ding

Randomized Smoothing (RS) has been proven a promising method for endowing an arbitrary image classifier with certified robustness. However, the substantial uncertainty inherent in the high-dimensional isotropic Gaussian noise imposes the curse of dimensionality on RS. Specifically, the upper bound of ℓ₂ certified robustness radius provided by RS exhibits a diminishing trend with the expansion of the input dimension d, proportionally decreasing at a rate of 1/√(d). This paper explores the feasibility of providing ℓ₂ certified robustness for high-dimensional input through the utilization of dual smoothing in the lower-dimensional space. The proposed Dual Randomized Smoothing (DRS) down-samples the input image into two sub-images and smooths the two sub-images in lower dimensions. Theoretically, we prove that DRS guarantees a tight ℓ₂ certified robustness radius for the original input and reveal that DRS attains a superior upper bound on the ℓ₂ robustness radius, which decreases proportionally at a rate of (1/√(m) + 1/√(n) ) with m+n=d. Extensive experiments demonstrate the generalizability and effectiveness of DRS, which exhibits a notable capability to integrate with established methodologies, yielding substantial improvements in both accuracy and ℓ₂ certified robustness baselines of RS on the CIFAR-10 and ImageNet datasets. Code is available at https://github.com/xiasong0501/DRS.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2404.09586")

Code

Syntology Ran 7 of 10 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran · fixture could not drive it; 5 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

xiasong0501/drs officialmentioned in paperpytorch 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.

Code Syntology ran Syntology

10 samples harvested; 7 ran; 0 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
1ran · fixture could not drive it
5ran
3unverified

Licence: 10 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from xiasong0501/DRS. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

conv3x3 xiasong0501/DRS/archs/cifar_resnet.py official repository ran · our draft was wrong no licence file found · pointer only · fac5364e2f53c6db · report
entropy xiasong0501/DRS/imagenet_train_lowres_2.py official repository ran fingerprinted no licence file found · pointer only · 23f822c3d6d64a12 · report
get_low_res_data xiasong0501/drs/DDS/imagenet/DRM.py official repository ran · fixture could not drive it no licence file found · pointer only · a16b11c89a38dfca · report
get_low_res_data xiasong0501/DRS/core1_lowres_2.py official repository ran no licence file found · pointer only · 966d9e557ce5aa94 · report
get_low_res_data xiasong0501/DRS/imagenet_train_lowres_2.py official repository ran no licence file found · pointer only · 4d4b1a4a3fc08e85 · report
get_upper_res_data xiasong0501/DRS/core1_lowres_2.py official repository ran no licence file found · pointer only · 3cd8ab8f4217978f · report
kl_div xiasong0501/DRS/imagenet_train_lowres_2.py official repository ran fingerprinted no licence file found · pointer only · 74325f9c5d49ca67 · report
dali_data xiasong0501/DRS/imagenet_model_lower_2.py official repository unverified no licence file found · pointer only · 54e10cf0f3dd3389 · report
get_imagenet_iter_torch xiasong0501/DRS/imagenet_dali.py official repository unverified no licence file found · pointer only · 6ddacd69764c3835 · report
get_low_res_data_mn xiasong0501/DRS/core1_lowres_2.py official repository unverified no licence file found · pointer only · a1abf4153e3f406a · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

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