Papers › On the detection of synthetic images generated by diffusion models

On the detection of synthetic images generated by diffusion models

1 Nov 2022arXiv:2211.00680archive 2025-07-28

Riccardo Corvi, Davide Cozzolino, Giada Zingarini, Giovanni Poggi, Koki Nagano, Luisa Verdoliva

Over the past decade, there has been tremendous progress in creating synthetic media, mainly thanks to the development of powerful methods based on generative adversarial networks (GAN). Very recently, methods based on diffusion models (DM) have been gaining the spotlight. In addition to providing an impressive level of photorealism, they enable the creation of text-based visual content, opening up new and exciting opportunities in many different application fields, from arts to video games. On the other hand, this property is an additional asset in the hands of malicious users, who can generate and distribute fake media perfectly adapted to their attacks, posing new challenges to the media forensic community. With this work, we seek to understand how difficult it is to distinguish synthetic images generated by diffusion models from pristine ones and whether current state-of-the-art detectors are suitable for the task. To this end, first we expose the forensics traces left by diffusion models, then study how current detectors, developed for GAN-generated images, perform on these new synthetic images, especially in challenging social-networks scenarios involving image compression and resizing. Datasets and code are available at github.com/grip-unina/DMimageDetection.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2211.00680")

Code

Syntology Ran 18 of 20 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 3 ran · our draft was wrong; 15 ran with no contract checked.

By repository: official repository: 20 samples from 1 repository, 18 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

grip-unina/dmimagedetection officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
AniSundar18/AlignedForensics mentioned on GitHubpytorch 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.

Code Syntology ran Syntology

20 samples harvested; 18 ran; 0 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

3ran · our draft was wrong
15ran
2unverified

Licence: 0 of the 20 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 grip-unina/dmimagedetection. “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. “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.

Each sample ends with its 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.

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 from a repository marked official are listed first. 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 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 label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

calculate_eer grip-unina/dmimagedetection/test_code/dmetrics.py official repository ran fingerprinted Apache-2.0 (permissive) · 0cf19471e87a45c2 · report
center_crop grip-unina/dmimagedetection/test_code/normalization.py official repository ran Apache-2.0 (permissive) · 6b872402efcb1483 · report
check_img grip-unina/dmimagedetection/test_code/csv_operations.py official repository ran Apache-2.0 (permissive) · be47a06dbf02938c · report
conv1x1 grip-unina/dmimagedetection/test_code/networks/resnet.py official repository ran · our draft was wrong Apache-2.0 (permissive) · d9def42110729a85 · report
conv3x3 grip-unina/dmimagedetection/test_code/networks/resnet.py official repository ran · our draft was wrong Apache-2.0 (permissive) · fac5364e2f53c6db · report
conv3x3 grip-unina/dmimagedetection/test_code/networks/resnet_mod.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 67c9ab8e625b4e5f · report
get_bal_sampler grip-unina/dmimagedetection/training_code/utils/dataset.py official repository ran Apache-2.0 (permissive) · b77e8d2f3ae99b82 · report
get_list_norm grip-unina/dmimagedetection/test_code/normalization.py official repository ran Apache-2.0 (permissive) · 436664f4ff92f847 · report
get_method_here grip-unina/dmimagedetection/test_code/get_method_here.py official repository ran Apache-2.0 (permissive) · 8e16d042fbf592d9 · report
macc grip-unina/dmimagedetection/test_code/dmetrics.py official repository ran fingerprinted Apache-2.0 (permissive) · 6a626b600adb420b · report
normalization_fft grip-unina/dmimagedetection/test_code/normalization.py official repository ran fingerprinted Apache-2.0 (permissive) · a639fc58d11576d3 · report
padding_wrap grip-unina/dmimagedetection/test_code/normalization2.py official repository ran Apache-2.0 (permissive) · 6ccd7d166120f68e · report
pd_at_far grip-unina/dmimagedetection/test_code/dmetrics.py official repository ran Apache-2.0 (permissive) · c1cd563a01ddb7e3 · report
resnet18 grip-unina/dmimagedetection/test_code/networks/resnet.py official repository ran Apache-2.0 (permissive) · d586be93da3254ed · report
resnet18 grip-unina/dmimagedetection/test_code/networks/resnet_mod.py official repository ran Apache-2.0 (permissive) · 1ab046e413eb720a · report
resnet18 grip-unina/dmimagedetection/training_code/networks/resnet_mod.py official repository ran Apache-2.0 (permissive) · ea87c5c696f3e8f4 · report
rule_minmax grip-unina/dmimagedetection/test_code/get_method_here.py official repository ran fingerprinted Apache-2.0 (permissive) · 1601acbe295e6729 · report
rule_trim grip-unina/dmimagedetection/test_code/get_method_here.py official repository ran Apache-2.0 (permissive) · 18315f3fd5065642 · report
add_dataloader_arguments grip-unina/dmimagedetection/training_code/utils/dataset.py official repository unverified Apache-2.0 (permissive) · 0db59a5c1784496d · report
get_dataset grip-unina/dmimagedetection/training_code/utils/dataset.py official repository unverified Apache-2.0 (permissive) · 96beb5997283006e · report

Tasks

Image Compression

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

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