Home › Code › PreActResNet18

PreActResNet18

Syntologyentry name in harvested coderead from the graph 2026-09-24

PreActResNet18 appears in the code Syntology harvested for 38 papers, as 26 distinct code bodies found in 40 places (a place is one code body under one paper). At least one of them ran in 19 of the papers; 0 of the code bodies carry a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named PreActResNet18 do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 12 of the 26 distinct code bodies named PreActResNet18; 14 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
3ran · our draft was wrong
0ran · fixture could not drive it
9ran
14unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 14 of the 40 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “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, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

38 papers shown of 38, newest first; 40 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 2 papers added by Syntology; 4 papers have no page here and are shown by arXiv id only. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's 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.

PaperDateFileStatus SyntologyLicence
SORA: Free Second-Order Attacks in Fast Adversarial Training added by Syntology 2026-06 (from id) HuangZhiChao95/ATAS/models/preact_resnet.py 40db4256aab2ed92 ran no licence file found · pointer only
SORA: Free Second-Order Attacks in Fast Adversarial Training added by Syntology 2026-06 (from id) tmllab/2023_NeurIPS_AAER/CIFAR10/preact_resnet.py 0234f49f9592dec8 ran MIT (permissive)
Detecting Semantic Backdoors in a Mystery Shopping Scenario added by Syntology 2026-01 (from id) szegedai/SemanticBackdoorDetection/models/preact_resnet.py a55348359ff9d8f1 unverified no licence file found · pointer only
Robust Classification by Coupling Data Mollification with Label Smoothing 3 Jun 2024 markusheinonen/supervised-mollification/src/networks/presnet.py 397de955665b5839 ran no licence file found · pointer only
arXiv:2406.01130 2024-06 (from id) skezle/sava/models/preact_resnet.py 84bbb44718624598 ran no licence file found · pointer only
Invisible Backdoor Attacks on Diffusion Models 2 Jun 2024 linweiii/backdoordm/classifier_models/preact_resnet.py 4427a19ae0928cb2 unverified MIT (permissive)
Jointly Modeling Inter- & Intra-Modality Dependencies for Multi-modal Learning 27 May 2024 divyam3897/i2m2/fastMRI/models/preactresnet_knee.py 96037b0c5b8c3511 unverified MIT (permissive)
Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency 25 May 2024 tmllab/2024_ICML_LAP/CIFAR10/preact_resnet.py 0234f49f9592dec8 ran MIT (permissive)
Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency 25 May 2024 tmllab/2024_ICML_LAP/Tiny-imagenet/preact_resnet.py 12838ecee21bc861 ran MIT (permissive)
Uniformly Stable Algorithms for Adversarial Training and Beyond 3 May 2024 jiancongxiao/moreau-envelope-sgd/adversarial_robustness_overfitting/preactresnet.py 1153837ba4a94242 ran no licence file found · pointer only
The Victim and The Beneficiary: Exploiting a Poisoned Model to Train a Clean Model on Poisoned Data 17 Apr 2024 zixuan-zhu/vab/models/preact_resnet.py a55348359ff9d8f1 unverified no licence file found · pointer only
Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization 11 Apr 2024 tmllab/2023_neurips_aaer/CIFAR10/preact_resnet.py 0234f49f9592dec8 ran MIT (permissive)
$σ$-zero: Gradient-based Optimization of $\ell_0$-norm Adversarial Examples 2 Feb 2024 cinofix/sigma-zero-adversarial-attack/models/cifar10/preact_resnet.py 88e37f205195a51a unverified no licence file found · pointer only
DAFA: Distance-Aware Fair Adversarial Training 23 Jan 2024 rucy74/DAFA/models/preact_resnet.py 1153837ba4a94242 ran no licence file found · pointer only
On the Robustness of Neural Collapse and the Neural Collapse of Robustness 13 Nov 2023 jingtongsu/robust_neural_collapse/preactresnet.py ab48c8c3bd0271a7 ran no licence file found · pointer only
On the Over-Memorization During Natural, Robust and Catastrophic Overfitting 13 Oct 2023 tmllab/2024_ICLR_DOM/preactresnet.py 1153837ba4a94242 ran MIT (permissive)
Fast Adversarial Training with Smooth Convergence 24 Aug 2023 FAT-CS/ConvergeSmooth/models/preact_resnet.py 10a42e5434d0fdcd ran no licence file found · pointer only
Understanding the robustness difference between stochastic gradient descent and adaptive gradient methods 13 Aug 2023 averyma/opt-robust/models/preact_resnet.py 6bc11692e189a289 ran no licence file found · pointer only
Adversarial Feature Map Pruning for Backdoor 21 Jul 2023 retsuh-bqw/FMP/models/preact_resnet.py a55348359ff9d8f1 unverified no licence file found · pointer only
Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples 20 Jul 2023 shawkui/Shared_Adversarial_Unlearning/models/preact_resnet.py a55348359ff9d8f1 unverified no licence file found · pointer only
Certified Robust Neural Networks: Generalization and Corruption Resistance 3 Mar 2023 ryanlucas3/hr_neural_networks/HR_Neural_Networks/Paper_experiments/Section_6.2/preactresnet.py 1153837ba4a94242 ran MIT (permissive)
ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning Paradigms 22 Feb 2023 ruoxi-jia-group/asset/models/preact_resnet.py b6e5f24824f19914 unverified MIT (permissive)
Revisiting adversarial training for the worst-performing class 17 Feb 2023 lions-epfl/class-focused-online-learning-code/cfol/preactresnet.py 1153837ba4a94242 ran MIT (permissive)
Rethinking the Reverse-engineering of Trojan Triggers 27 Oct 2022 ru-system-software-and-security/featurere/models/preact_resnet.py 8c9f324e2ca8f8ff unverified MIT (permissive)
Scaling Adversarial Training to Large Perturbation Bounds 18 Oct 2022 val-iisc/OAAT/models/preactresnet.py 6720f86e06ca335e unverified MIT (permissive)
A2: Efficient Automated Attacker for Boosting Adversarial Training 7 Oct 2022 alipay/A2-efficient-automated-attacker-for-boosting-adversarial-training/preactresnet.py 1153837ba4a94242 ran Apache-2.0 (permissive)
BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning 26 May 2022 ru-system-software-and-security/bppattack/classifier_models/preact_resnet.py 009ef5196808279a unverified MIT (permissive)
Using Multiple Self-Supervised Tasks Improves Model Robustness 7 Apr 2022 mattlawhon/SelfSupDefense/learning/preactresnet.py 1153837ba4a94242 ran Apache-2.0 (permissive)
Robust Training under Label Noise by Over-parameterization 28 Feb 2022 shengliu66/sop/model/PreResNet.py bf41d63bb259c163 unverified MIT (permissive)
Fast Certified Robust Training with Short Warmup 31 Mar 2021 shizhouxing/Fast-Certified-Robust-Training/models/resnet.py abc02d2c96c29b28 unverified BSD-3-Clause (permissive)
Adversarial Attacks are Reversible with Natural Supervision 26 Mar 2021 cvlab-columbia/SelfSupDefense/learning/preactresnet.py 1153837ba4a94242 ran Apache-2.0 (permissive)
Noisy Concurrent Training for Efficient Learning under Label Noise 17 Sep 2020 NeurAI-Lab/NCT/models/preact_resnet.py 08458e1871e2fd5f ran · our draft was wrong MIT (permissive)
ReZero is All You Need: Fast Convergence at Large Depth 10 Mar 2020 statsu1990/ReZero-Cifar100/src/model/rezero_preact_resnet.py 09aa6bbcdc551903 ran · our draft was wrong MIT (permissive)
Fast is better than free: Revisiting adversarial training 12 Jan 2020 tml-epfl/understanding-fast-adv-training/models.py fa636f649fc7a458 ran · our draft was wrong no licence file found · pointer only
Ordered SGD: A New Stochastic Optimization Framework for Empirical Risk Minimization 9 Jul 2019 kenjikawaguchi/qSGD/models/preact_resnet.py 61182bd4fcf9cc8d unverified MIT (permissive)
Network Deconvolution 28 May 2019 deconvolutionpaper/deconvolution/models/preact_resnet.py 8b6f2206042fed23 unverified Apache-2.0 (permissive)
mixup: Beyond Empirical Risk Minimization 25 Oct 2017 leehomyc/mixup_pytorch/models/preact_resnet.py b6e5f24824f19914 unverified MIT (permissive)
arXiv:aaai_29250 Feng-peng-Li/Regroup-Loss-Median-to-Combat-Label-Noise/networks/ResNet.py 9d76ba3eb64583df unverified MIT (permissive)
arXiv:aaai_28019 VinAIResearch/COMBAT/classifier_models/preact_resnet.py 1dfacc8b74dc8780 unverified MIT (permissive)
arXiv:Pang_Backdoor_Cleansing_With_Unlabeled_Data_CVPR_2023_paper luluppang/BCU/models/preact_resnet.py a55348359ff9d8f1 unverified MIT (permissive)

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the 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 cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

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