Papers › FaceForensics++: Learning to Detect Manipulated Facial Images

FaceForensics++: Learning to Detect Manipulated Facial Images

25 Jan 2019arXiv:1901.08971archive 2025-07-28

Andreas Rössler, Davide Cozzolino, Luisa Verdoliva, Christian Riess, Justus Thies, Matthias Nießner

The rapid progress in synthetic image generation and manipulation has now come to a point where it raises significant concerns for the implications towards society. At best, this leads to a loss of trust in digital content, but could potentially cause further harm by spreading false information or fake news. This paper examines the realism of state-of-the-art image manipulations, and how difficult it is to detect them, either automatically or by humans. To standardize the evaluation of detection methods, we propose an automated benchmark for facial manipulation detection. In particular, the benchmark is based on DeepFakes, Face2Face, FaceSwap and NeuralTextures as prominent representatives for facial manipulations at random compression level and size. The benchmark is publicly available and contains a hidden test set as well as a database of over 1.8 million manipulated images. This dataset is over an order of magnitude larger than comparable, publicly available, forgery datasets. Based on this data, we performed a thorough analysis of data-driven forgery detectors. We show that the use of additional domainspecific knowledge improves forgery detection to unprecedented accuracy, even in the presence of strong compression, and clearly outperforms human observers.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also 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

Syntology 9 code samples harvested from 3 repositories linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 4 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 8 samples from 2 repositories, 8 ran (8 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

14 repositories listed; official and paper-mentioned ones first.

ondyari/FaceForensics officialmentioned in papermentioned on GitHubSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
Baukebrenninkmeijer/HackGAN mentioned on GitHubNOASSERTIONSyntology: not harvested report
SuyashSonawane/fakedetector mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
flynn-chen/faceforensics_benchmark mentioned on GitHubNOASSERTIONSyntology: not harvested report
jhchang/DFDC mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Video Face Manipulation Detection Through Ensemble of CNNs (arXiv:2004.07676; that paper's own run record: 1 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; 1 where Syntology's instrument failed) · 2 unverified) and The DeepFake Detection Challenge (DFDC) Dataset (arXiv:2006.07397; that paper's own run record: 1 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; 1 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
polimi-ispl/icpr2020dfdc mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
pothabattulasantosh/Detection-of-face-Manipulated-videos mentioned on GitHubSyntology: not harvested report
pothabattulasantosh/Detection-of-facial-Manipulated-videos mentioned on GitHubSyntology: not harvested report
seongilp/DFE604-2020F-FinalProject mentioned on GitHubSyntology: not harvested report
twyunting/Deepfake_Video_Classifier mentioned on GitHubMITSyntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified report
yyk-wew/F3Net mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
tamlhp/dfd_benchmark pytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Comprehensive Survey with Critical Analysis for Deepfake Speech Detection (arXiv:2409.15180; that paper's own run record: 12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. 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

9 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 4 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · honoured contract
5ran

Licence: 4 of the 9 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 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

ondyari/FaceForensics official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
get_boundingbox classification/detect_from_video.py ran · honoured contract licence not identified · pointer only · cdd770694303a504 · report fixture: signature face:MockDlibFace/0/?, width:int/0/int, height:int/0/int, scale:float/0/float, minsize:int/0/int · returned tuple · level recorded 2026-09-22
twyunting/Deepfake_Video_Classifier community (archive-listed) 5 samples, 5 ran (0 instrument-failed) · 0 unverified
get_all_image_files_read code/HPC/HPC_construct_xfeatures_ylabels.py ran MIT (permissive) · d3ab7e011ae90f2f · report fixture: signature path:str/0/str, filenames:list/1/str · returned list · level recorded 2026-09-24
get_list_filenames code/HPC/HPC_construct_xfeatures_ylabels.py ran MIT (permissive) · 06cdb128fdc7a477 · report fixture: signature cwd:str/0/str, path:str/0/str, extension:str/0/str · returned list · level recorded 2026-09-24
meanSubtraction code/HPC/D_fake.py ran MIT (permissive) · faa064775cbc66a2 · report fixture: signature arr:list/1/ndarray · returned ndarray · level recorded 2026-09-24
meanSubtraction code/HPC/D_real.py ran MIT (permissive) · 8875205c75575c51 · report fixture: signature arr:list/1/ndarray · returned ndarray · level recorded 2026-09-24
svdTraining code/HPC/D_fake.py ran MIT (permissive) · 50149f89fd20f79e · report fixture: signature arr:list/1/ndarray · returned tuple · level recorded 2026-09-24
yyk-wew/F3Net community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
DCT_mat models.py ran · honoured contract fingerprinted no licence file found · pointer only · 97170801bfeabdb7 · report fixture: signature size:int/0/int · returned list · level recorded 2026-09-22
generate_filter models.py ran · honoured contract no licence file found · pointer only · 61e9294462032ca0 · report fixture: signature start:int/0/int, end:int/0/int, size:int/0/int · returned list · level recorded 2026-09-22
norm_sigma models.py ran · honoured contract fingerprinted no licence file found · pointer only · 22f1a0ed4d350586 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22

Tasks

DeepFake DetectionFace SwappingFake Image DetectionImage Generation

Datasets

Introduced by this paper, per the archive.

FaceForensics++

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
DeepFake Detection FaceForensics XceptionNet DF 96.36 #1 of 1 Archive leaderboard report
DeepFake Detection FaceForensics XceptionNet FS 90.29 #1 of 1 Archive leaderboard report
DeepFake Detection FaceForensics XceptionNet FSF 86.86 #1 of 1 Archive leaderboard report
DeepFake Detection FaceForensics XceptionNet NT 80.67 #1 of 1 Archive leaderboard report
DeepFake Detection FaceForensics XceptionNet Real 52.4 #1 of 1 Archive leaderboard report
DeepFake Detection FaceForensics XceptionNet Total Accuracy 70.1 #1 of 1 Archive leaderboard report
DeepFake Detection FakeAVCeleb Xception AP 84.8 #7 of 13 Archive leaderboard report
DeepFake Detection FakeAVCeleb Xception ROC AUC 85.3 #7 of 13 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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