Papers › Which Models have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustness

Which Models have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustness

30 May 2023NeurIPS 2023 11arXiv:2305.19101archive 2025-07-28

Suraj Srinivas, Sebastian Bordt, Hima Lakkaraju

One of the remarkable properties of robust computer vision models is that their input-gradients are often aligned with human perception, referred to in the literature as perceptually-aligned gradients (PAGs). Despite only being trained for classification, PAGs cause robust models to have rudimentary generative capabilities, including image generation, denoising, and in-painting. However, the underlying mechanisms behind these phenomena remain unknown. In this work, we provide a first explanation of PAGs via off-manifold robustness, which states that models must be more robust off- the data manifold than they are on-manifold. We first demonstrate theoretically that off-manifold robustness leads input gradients to lie approximately on the data manifold, explaining their perceptual alignment. We then show that Bayes optimal models satisfy off-manifold robustness, and confirm the same empirically for robust models trained via gradient norm regularization, randomized smoothing, and adversarial training with projected gradient descent. Quantifying the perceptual alignment of model gradients via their similarity with the gradients of generative models, we show that off-manifold robustness correlates well with perceptual alignment. Finally, based on the levels of on- and off-manifold robustness, we identify three different regimes of robustness that affect both perceptual alignment and model accuracy: weak robustness, bayes-aligned robustness, and excessive robustness. Code is available at https://github.com/tml-tuebingen/pags.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also 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

Syntology 11 code samples harvested from 2 repositories linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 5 samples from 1 repository, 5 ran (0 with no instrument failure; 5 where Syntology's instrument failed); found in paper text by Syntology: 6 samples from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

tml-tuebingen/pags officialmentioned in paperpytorchSyntology: 5 samples, 5 ran (5 instrument-failed) · 0 unverified 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

11 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
2ran; the contract check could not run
1ran
5unverified

Licence: 0 of the 11 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

tml-tuebingen/pags official repository 5 samples, 5 ran (5 instrument-failed) · 0 unverified
dict2options run_experiments.py ran · our draft was wrong MIT (permissive) · 05d569aa12038fae · report fixture: signature settings:dict/0/? · returned tuple · level recorded 2026-09-22
get_optimizer_scheduler train_models.py ran · our draft was wrong MIT (permissive) · 0d11fdf711dd6e20 · report fixture: signature args:Args/0/?, model:callable/0/? · returned tuple · level recorded 2026-09-22
measure_on_off_manifold_robustness experiments/measure_manifold_robustness.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic MIT (permissive) · 65b5172b3691e86a · report fixture: signature model:callable/0/?, test_loader:list/1/tuple, test_tangent_spaces:list/1/Tensor, device:device/0/?, N_images:int/0/int · returned tuple · level recorded 2026-09-22
project_into_tangent_space experiments/measure_manifold_robustness.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 58244b9a6e3b6f31 · report fixture: signature tangent_space:ndarray/4/float, vector:ndarray/3/float · returned ndarray · level recorded 2026-09-22
softmax_l1 experiments/measure_manifold_robustness.py ran · our draft was wrong fingerprinted MIT (permissive) · d401cbdf3efe9b60 · report fixture: signature x:Tensor/2/float, y:Tensor/2/float · returned Tensor · level recorded 2026-09-22
MadryLab/robustness found in paper text by Syntology 6 samples, 1 ran (0 instrument-failed) · 5 unverified
add_args_to_parser robustness/defaults.py ran MIT (permissive) · 078da01e51a28471 · report fixture: signature arg_list:list/1/list, parser:ArgumentParser/0/? · returned ArgumentParser · level recorded 2026-09-24
alexnet in 42 papers robustness/imagenet_models/alexnet.py unverified MIT (permissive) · 3b26d6ebbd9142b2 · report
densenet121 in 43 papers robustness/imagenet_models/densenet.py unverified MIT (permissive) · 85c4757ab3246b61 · report
densenet161 in 20 papers robustness/imagenet_models/densenet.py unverified MIT (permissive) · 6b70762b5419b176 · report
densenet169 in 42 papers robustness/imagenet_models/densenet.py unverified MIT (permissive) · 019686268f24b3b5 · report
model_dataset_from_store in 5 papers robustness/model_utils.py unverified MIT (permissive) · c1e41af537b4027c · report

Tasks

DenoisingImage Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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