SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.10174 · CVPR · 2023

Towards Universal Fake Image Detectors that Generalize Across Generative Models

Utkarsh Ojha, Yong Lee, Yuheng Li

arXiv · PDF · Open in the Atlas

Code that ran

11 of 16 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 0 have no contract verdict; 11 failures of our instrument; 5 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/2302.10174.json · badge: /api/ran/2302.10174.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.

RepositoryRoleRan
yuheng-li/universalfakedetect canonical (classifier label)
classifier basis not recorded on the link
11 ran · 5 no recorded run
FunctionStatusWhere it lives
conv1x1 Ran
ran; our contract draft was wrong, not the code
yuheng-li/universalfakedetect/networks/resnet_lpf.py
code served (permissive licence) · get_code("d9def42110729a85")
How it ran

Ran 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.

import torch
import torch.nn as nn

torch.manual_seed(0)

# The function conv1x1 takes in_planes, out_planes, and stride as parameters
# It returns an nn.Conv2d layer configured for 1x1 convolution
# We need to provide valid integer arguments for these parameters

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
conv1x1 Ran
ran; our contract draft was wrong, not the code
yuheng-li/universalfakedetect/models/resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from medaitech/scrd4ad, is pointer only (licence: NONE) · get_code("2a80220dabcb742a")
How it ran

The 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 medaitech/scrd4ad, 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
yuheng-li/universalfakedetect/models/resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from medaitech/scrd4ad, is pointer only (licence: NONE) · get_code("600ff2c45e0de056")
How it ran

The 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 medaitech/scrd4ad, 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
yuheng-li/universalfakedetect/networks/resnet_lpf.py
pointer only (licence: MIT); the stored copy get_code serves, from ChrisMats/Res2Net, is pointer only (licence: NONE) · get_code("e18ed73aa89f051a")
How it ran

The 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 ChrisMats/Res2Net, 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.

draw_bounding_boxes Ran
ran; our contract draft was wrong, not the code
yuheng-li/universalfakedetect/models/vision_transformer_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from manyilee/plada, is pointer only (licence: NONE) · get_code("59965ca4b20cd0a3")
How it ran

The 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 manyilee/plada, 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.

draw_segmentation_masks Ran
ran; our contract draft was wrong, not the code
yuheng-li/universalfakedetect/models/vision_transformer_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from manyilee/plada, is pointer only (licence: NONE) · get_code("54fd90bd934c47e1")
How it ran

The 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 manyilee/plada, 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.

get_pad_layer Ran
ran; our contract draft was wrong, not the code
yuheng-li/universalfakedetect/networks/lpf.py
pointer only (licence: MIT); the stored copy get_code serves, from linwei-chen/seg-aliasing, is pointer only (licence: NONE) · get_code("50aa4a59fe718c61")
How it ran

The 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 linwei-chen/seg-aliasing, 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.

get_pad_layer_1d Ran
ran; our contract draft was wrong, not the code
yuheng-li/universalfakedetect/networks/lpf.py
pointer only (licence: MIT); the stored copy get_code serves, from Ekko-zn/AIGCDetectBenchmark, is pointer only (licence: NONE) · get_code("176a539246e68879")
How it ran

The 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.

make_grid Ran
ran; our contract draft was wrong, not the code
yuheng-li/universalfakedetect/models/vision_transformer_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from manyilee/plada, is pointer only (licence: NONE) · get_code("8c3d0e690efa99fe")
How it ran

The 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 manyilee/plada, 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.

vgg11 Ran
ran; our contract draft was wrong, not the code
yuheng-li/universalfakedetect/models/vgg.py
pointer only (licence: MIT); the stored copy get_code serves, from manyilee/plada, is pointer only (licence: NONE) · get_code("04cac479388fed8d")
How it ran

The 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 manyilee/plada, 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.

vgg19 Ran
ran; our contract draft was wrong, not the code
yuheng-li/universalfakedetect/models/vgg.py
pointer only (licence: MIT); the stored copy get_code serves, from manyilee/plada, is pointer only (licence: NONE) · get_code("36aa35f7d5c690bd")
How it ran

The 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 manyilee/plada, 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.

resnet18 Not yet run
unverified (harvested, no recorded run)
yuheng-li/universalfakedetect/models/resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from manyilee/plada, is pointer only (licence: NONE) · get_code("cd4a0cb7c1c3bb95")
How it ran

The 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 manyilee/plada, 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. No invocation recorded.

resnet18 Not yet run
unverified (harvested, no recorded run)
yuheng-li/universalfakedetect/networks/resnet_lpf.py
code served (permissive licence) · get_code("768d1f99fcf02b79")
How it ran

no invocation recorded.

vit_b_16 Not yet run
unverified (harvested, no recorded run)
yuheng-li/universalfakedetect/models/vision_transformer.py
pointer only (licence: MIT); the stored copy get_code serves, from manyilee/plada, is pointer only (licence: NONE) · get_code("e3760b265536dca0")
How it ran

The 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 manyilee/plada, 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. No invocation recorded.

vit_b_32 Not yet run
unverified (harvested, no recorded run)
yuheng-li/universalfakedetect/models/vision_transformer.py
pointer only (licence: MIT); the stored copy get_code serves, from manyilee/plada, is pointer only (licence: NONE) · get_code("e2038eb9ae534f89")
How it ran

The 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 manyilee/plada, 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. No invocation recorded.

vit_l_16 Not yet run
unverified (harvested, no recorded run)
yuheng-li/universalfakedetect/models/vision_transformer.py
pointer only (licence: MIT); the stored copy get_code serves, from manyilee/plada, is pointer only (licence: NONE) · get_code("4d461a68c1030630")
How it ran

The 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 manyilee/plada, 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. No invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 15 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 1 the same month, 15 later) and 1 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.

FunctionAlso present inEarliest-datedOthers named
conv1x1 431 other papers
240 dated earlier, 5 the same month, 177 later, 8 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
conv1x1 112 other papers
37 dated earlier, 73 later, 2 same year, order not determinable · 6 only as an assembly brick
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1806.01531 (2018-06)
Deep Mixture of Experts via Shallow Embedding
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
and 109 more not named here
conv3x3 111 other papers
38 dated earlier, 71 later, 2 same year, order not determinable · 6 only as an assembly brick
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1806.01531 (2018-06)
Deep Mixture of Experts via Shallow Embedding
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
and 108 more not named here
resnet18 36 other papers
16 dated earlier, 20 later
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
2002.09564 (2020-02)
Towards Robust and Reproducible Active Learning Using Neural Networks
2003.04297 (2020-03)
Improved Baselines with Momentum Contrastive Learning
and 33 more not named here
get_pad_layer 25 other papers
10 dated earlier, 14 later, 1 same year, order not determinable · 3 only as an assembly brick
2004.09484 (2020-04)
Bringing Old Photos Back to Life
2007.15651 (2020-07)
Contrastive Learning for Unpaired Image-to-Image Translation
2008.09604 (2020-08)
Delving Deeper into Anti-aliasing in ConvNets
and 22 more not named here
conv3x3 13 other papers
10 dated earlier, 2 later, 1 same year, order not determinable · 1 only as an assembly brick
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1904.01169 (2019-04)
Res2Net: A New Multi-scale Backbone Architecture
1907.11561 (2019-07)
Deep Learning for Classification and Severity Estimation of Coffee Leaf Biotic Stress
and 10 more not named here
get_pad_layer_1d 8 other papers
3 dated earlier, 5 later
2112.09130 (2021-12)
Ensembling Off-the-shelf Models for GAN Training
2204.05841 (2022-04)
VoiceFixer: A Unified Framework for High-Fidelity Speech Restoration
2207.13686 (2022-07)
Shift-tolerant Perceptual Similarity Metric
and 5 more not named here
draw_bounding_boxes 1 other paper
1 later
2506.20548 (2025-06)
Pay Less Attention to Deceptive Artifacts: Robust Detection of Compressed Deepfakes on Online Social Networks
draw_segmentation_masks 1 other paper
1 later
2506.20548 (2025-06)
Pay Less Attention to Deceptive Artifacts: Robust Detection of Compressed Deepfakes on Online Social Networks
make_grid 1 other paper
1 later
2506.20548 (2025-06)
Pay Less Attention to Deceptive Artifacts: Robust Detection of Compressed Deepfakes on Online Social Networks
vgg11 1 other paper
1 later
2506.20548 (2025-06)
Pay Less Attention to Deceptive Artifacts: Robust Detection of Compressed Deepfakes on Online Social Networks
vgg19 1 other paper
1 later
2506.20548 (2025-06)
Pay Less Attention to Deceptive Artifacts: Robust Detection of Compressed Deepfakes on Online Social Networks
vit_b_16 1 other paper
1 later
2506.20548 (2025-06)
Pay Less Attention to Deceptive Artifacts: Robust Detection of Compressed Deepfakes on Online Social Networks
vit_b_32 1 other paper
1 later
2506.20548 (2025-06)
Pay Less Attention to Deceptive Artifacts: Robust Detection of Compressed Deepfakes on Online Social Networks
vit_l_16 1 other paper
1 later
2506.20548 (2025-06)
Pay Less Attention to Deceptive Artifacts: Robust Detection of Compressed Deepfakes on Online Social Networks

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.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

With generative models proliferating at a rapid rate, there is a growing need for general purpose fake image detectors. In this work, we first show that the existing paradigm, which consists of training a deep network for real-vs-fake classification, fails to detect fake images from newer breeds of generative models when trained to detect GAN fake images. Upon analysis, we find that the resulting classifier is asymmetrically tuned to detect patterns that make an image fake. The real class becomes a 'sink' class holding anything that is not fake, including generated images from models not accessible during training. Building upon this discovery, we propose to perform real-vs-fake classification without learning; i.e., using a feature space not explicitly trained to distinguish real from fake images. We use nearest neighbor and linear probing as instantiations of this idea. When given access to the feature space of a large pretrained vision-language model, the very simple baseline of nearest neighbor classification has surprisingly good generalization ability in detecting fake images from a wide variety of generative models; e.g., it improves upon the SoTA [50] by +15.07 mAP and +25.90% acc when tested on unseen diffusion and autoregressive models. Our code, models, and data can be found at https://github.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2302.10174")
get_code_for_paper("2302.10174")
have("2302.10174")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2302.10174.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2302.10174.svg)](https://syntology.ai/paper/2302.10174)

Connect an agent — have() is free.