Papers › Certified Patch Robustness via Smoothed Vision Transformers

Certified Patch Robustness via Smoothed Vision Transformers

11 Oct 2021CVPR 2022 1arXiv:2110.07719archive 2025-07-28

Hadi Salman, Saachi Jain, Eric Wong, Aleksander Mądry

Certified patch defenses can guarantee robustness of an image classifier to arbitrary changes within a bounded contiguous region. But, currently, this robustness comes at a cost of degraded standard accuracies and slower inference times. We demonstrate how using vision transformers enables significantly better certified patch robustness that is also more computationally efficient and does not incur a substantial drop in standard accuracy. These improvements stem from the inherent ability of the vision transformer to gracefully handle largely masked images. Our code is available at https://github.com/MadryLab/smoothed-vit.

PaperPDFConference PDFCodeCode 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="2110.07719")

Code

Syntology Ran 6 of 10 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 2 ran · fixture could not drive it; 4 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

madrylab/smoothed-vit officialmentioned in papermentioned on GitHubpytorchMIT 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; 6 ran; 0 honoured the contract we drafted; 4 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.

2ran · fixture could not drive it
4ran
4unverified

Licence: 0 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 madrylab/smoothed-vit. “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.

ablate madrylab/smoothed-vit/src/utils/smoothing.py official repository ran MIT (permissive) · 9f7dbcd11d378c8d · report
ablate2 madrylab/smoothed-vit/src/utils/smoothing.py official repository ran MIT (permissive) · 66c46159973cca31 · report
drop_block_2d madrylab/smoothed-vit/src/utils/custom_models/layers/drop.py official repository ran MIT (permissive) · 33efc9f1ccc7933c · report
drop_block_fast_2d madrylab/smoothed-vit/src/utils/custom_models/layers/drop.py official repository ran MIT (permissive) · 30d63ccefb97a166 · report
drop_path madrylab/smoothed-vit/src/utils/custom_models/layers/drop.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 3ac6b7d76e8e3584 · report
trunc_normal_ madrylab/smoothed-vit/src/utils/custom_models/layers/weight_init.py official repository ran · fixture could not drive it MIT (permissive) · 02566da69866c48c · report
certify madrylab/smoothed-vit/src/utils/smoothing.py official repository unverified MIT (permissive) · 5ec101dbc1fa66d0 · report
vit_base_patch16_224 madrylab/smoothed-vit/src/utils/custom_models/vision_transformer.py official repository unverified MIT (permissive) · b5560ea79c839c1d · report
vit_base_patch16_384 madrylab/smoothed-vit/src/utils/custom_models/vision_transformer.py official repository unverified MIT (permissive) · 660471bd5729d3b0 · report
vit_small_patch16_224 madrylab/smoothed-vit/src/utils/custom_models/vision_transformer.py official repository unverified MIT (permissive) · 9fd5a755657a7d0b · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionDense ConnectionsLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSoftmaxVision Transformer

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