6 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 3 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.
"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2203.14145.json · badge: /api/ran/2203.14145.svg
Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.
| Repository | Role | Ran |
|---|---|---|
| yifanfanfanfan/reverse-engineering-of-imperceptible-adversarial-image-perturbations | canonical (classifier label) classifier basis not recorded on the link |
6 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| conv1x1 | Ran ran; our contract draft was wrong, not the code |
yifanfanfanfan/reverse-engineering-of-imperceptible-adversarial-image-perturbations/archs/gan_resnet.py code served (permissive licence) · get_code("d9def42110729a85") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Conv2d. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| conv3x3 | Ran ran; our contract draft was wrong, not the code |
yifanfanfanfan/reverse-engineering-of-imperceptible-adversarial-image-perturbations/archs/cifar_resnet.py pointer only (licence: MIT); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db") How it ranThe body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from lixiaotong97/DSU, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| cosine_lr | Ran ran on a synthesized input |
yifanfanfanfan/reverse-engineering-of-imperceptible-adversarial-image-perturbations/RED_train_with_trans.py code served (permissive licence) · get_code("c5196b556b5ecc5a") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned function. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| psnr | Ran ran on a synthesized input |
yifanfanfanfan/reverse-engineering-of-imperceptible-adversarial-image-perturbations/Transform_Model.py code served (permissive licence) · get_code("1d07ecebecc6c604") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| resnet18 | Ran ran; our contract draft was wrong, not the code |
yifanfanfanfan/reverse-engineering-of-imperceptible-adversarial-image-perturbations/archs/gan_resnet.py pointer only (licence: MIT); the stored copy get_code serves, from Ekko-zn/AIGCDetectBenchmark, is pointer only (licence: NONE) · get_code("66dc6f0c9b782c56") How it ranThe body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Ekko-zn/AIGCDetectBenchmark, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| set_gpu | Ran ran on a synthesized input |
yifanfanfanfan/reverse-engineering-of-imperceptible-adversarial-image-perturbations/RED_train_with_trans.py code served (permissive licence) · get_code("6a19bfad60fac463") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned MinimalModel. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 3 the same month, 3 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).
Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.
| Function | Also present in | Earliest-dated | Others named |
|---|---|---|---|
| conv3x3 | 686 other papers 374 dated earlier, 11 the same month, 290 later, 11 same year, order not determinable · 31 only as an assembly brick |
1406.2661 (2014-06) Generative Adversarial Networks |
1409.0575 (2014-09) ImageNet Large Scale Visual Recognition Challenge 1412.6572 (2014-12) Explaining and Harnessing Adversarial Examples and 683 more not named here |
| conv1x1 | 431 other papers 174 dated earlier, 10 the same month, 235 later, 11 same year, order not determinable, 1 undated · 38 only as an assembly brick |
1409.1556 (2014-09) Very Deep Convolutional Networks for Large-Scale Image Recognition |
1506.01186 (2015-06) Cyclical Learning Rates for Training Neural Networks 1507.05717 (2015-07) An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition and 428 more not named here |
| resnet18 | 89 other papers 46 dated earlier, 2 the same month, 39 later, 2 same year, order not determinable |
1705.09759 (2017-05) CASENet: Deep Category-Aware Semantic Edge Detection |
1801.07698 (2018-01) ArcFace: Additive Angular Margin Loss for Deep Face Recognition 1803.00839 (2018-03) Pose-Robust Face Recognition via Deep Residual Equivariant Mapping and 86 more not named here |
Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
It has been well recognized that neural network based image classifiers are easily fooled by images with tiny perturbations crafted by an adversary. There has been a vast volume of research to generate and defend such adversarial attacks. However, the following problem is left unexplored: How to reverse-engineer adversarial perturbations from an adversarial image? This leads to a new adversarial learning paradigm--Reverse Engineering of Deceptions (RED). If successful, RED allows us to estimate adversarial perturbations and recover the original images. However, carefully crafted, tiny adversarial perturbations are difficult to recover by optimizing a unilateral RED objective. For example, the pure image denoising method may overfit to minimizing the reconstruction error but hardly preserve the classification properties of the true adversarial perturbations. To tackle this challenge, we formalize the RED problem and identify a set of principles crucial to the RED approach design. Particularly, we find that prediction alignment and proper data augmentation (in terms of spatial transformations) are two criteria to achieve a generalizable RED approach. By integrating these RED principles with image denoising, we propose a new Class-Discriminative Denoising based RED framework, termed CDD-RED. Extensive experiments demonstrate the effectiveness of CDD-RED under different evaluation metrics (ranging from the pixel-level, prediction-level to the attribution-level alignment) and a variety of attack generation methods (e.g., FGSM, PGD, CW, AutoAttack, and adaptive attacks).
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2203.14145")
get_code_for_paper("2203.14145")
have("2203.14145")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2203.14145.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2203.14145)
Connect an agent — have() is free.