Papers › CNN-generated images are surprisingly easy to spot... for now

CNN-generated images are surprisingly easy to spot... for now

23 Dec 2019CVPR 2020 6arXiv:1912.11035archive 2025-07-28

Sheng-Yu Wang, Oliver Wang, Richard Zhang, Andrew Owens, Alexei A. Efros

In this work we ask whether it is possible to create a "universal" detector for telling apart real images from these generated by a CNN, regardless of architecture or dataset used. To test this, we collect a dataset consisting of fake images generated by 11 different CNN-based image generator models, chosen to span the space of commonly used architectures today (ProGAN, StyleGAN, BigGAN, CycleGAN, StarGAN, GauGAN, DeepFakes, cascaded refinement networks, implicit maximum likelihood estimation, second-order attention super-resolution, seeing-in-the-dark). We demonstrate that, with careful pre- and post-processing and data augmentation, a standard image classifier trained on only one specific CNN generator (ProGAN) is able to generalize surprisingly well to unseen architectures, datasets, and training methods (including the just released StyleGAN2). Our findings suggest the intriguing possibility that today's CNN-generated images share some common systematic flaws, preventing them from achieving realistic image synthesis. Code and pre-trained networks are available at https://peterwang512.github.io/CNNDetection/ .

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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

PeterWang512/CNNDetection officialmentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
Michel-liu/FatFormer mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection (arXiv:2312.16649; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
yuheng-li/universalfakedetect mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Towards Universal Fake Image Detectors that Generalize Across Generative Models (arXiv:2302.10174; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
BoFeng2477/CNNDetection-TF2.0 tfGPL-3.0Syntology: not harvested report
Joool/ReproducabilityCNNEasyToSpot pytorchSyntology: not harvested 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Data AugmentationImage GenerationSuper-Resolution

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAdamAdaptive Instance NormalizationBatch NormalizationBigGANConditional Batch NormalizationConvolutionCycle Consistency LossDense ConnectionsEarly StoppingFeedforward NetworkGAN Hinge LossGAN Least Squares LossInstance NormalizationLinear LayerNon-Local BlockNon-Local OperationOff-Diagonal Orthogonal RegularizationPatchGANProjection DiscriminatorR1 RegularizationReLUResidual BlockResidual ConnectionSAGANSigmoid ActivationSoftmaxSpectral NormalizationStyleGANTTURTanh ActivationTestTruncation Trick

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