Papers › Multi-attentional Deepfake Detection

Multi-attentional Deepfake Detection

3 Mar 2021CVPR 2021 1arXiv:2103.02406archive 2025-07-28

Hanqing Zhao, Wenbo Zhou, Dongdong Chen, Tianyi Wei, Weiming Zhang, Nenghai Yu

Face forgery by deepfake is widely spread over the internet and has raised severe societal concerns. Recently, how to detect such forgery contents has become a hot research topic and many deepfake detection methods have been proposed. Most of them model deepfake detection as a vanilla binary classification problem, i.e, first use a backbone network to extract a global feature and then feed it into a binary classifier (real/fake). But since the difference between the real and fake images in this task is often subtle and local, we argue this vanilla solution is not optimal. In this paper, we instead formulate deepfake detection as a fine-grained classification problem and propose a new multi-attentional deepfake detection network. Specifically, it consists of three key components: 1) multiple spatial attention heads to make the network attend to different local parts; 2) textural feature enhancement block to zoom in the subtle artifacts in shallow features; 3) aggregate the low-level textural feature and high-level semantic features guided by the attention maps. Moreover, to address the learning difficulty of this network, we further introduce a new regional independence loss and an attention guided data augmentation strategy. Through extensive experiments on different datasets, we demonstrate the superiority of our method over the vanilla binary classifier counterparts, and achieve state-of-the-art performance.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 25 code samples harvested from 1 repository linked to this paper: 20 ran (of which 10 constructed an object rather than computing a result; 17 with no instrument failure: 3 honoured, 0 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 25 samples from 1 repository, 20 ran (17 with no instrument failure; 3 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.

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.

yoctta/multiple-attention officialmentioned in papermentioned on GitHubpytorchSyntology: 25 samples, 20 ran (3 instrument-failed) · 5 unverified 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

25 samples harvested: 20 ran (of which 10 constructed an object rather than computing a result; 17 with no instrument failure: 3 honoured, 0 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 5 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.

3ran · honoured contract
2ran · our draft was wrong
1ran; the contract check could not run
14ran
5unverified

Licence: 25 of the 25 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 yoctta/multiple-attention. “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”. For 7 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

yoctta/multiple-attention official repository 25 samples, 20 ran (3 instrument-failed) · 5 unverified
AttentionMap models/MAT.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 43d9801d323877e5 · report fixture: returned AttentionMap · level recorded 2026-09-22
AttentionPooling in 9 papers models/MAT.py ran no licence file found · pointer only · 020e1d7ced206b80 · report fixture: signature features:Tensor/4/float, attentions:Tensor/4/float, norm:int/0/int · returned Tensor · level recorded 2026-09-24
Auxiliary_Loss_v2 models/MAT.py ran · metamorphic tier: deterministic no licence file found · pointer only · ee64f50e0c084ee1 · report fixture: returned Auxiliary_Loss_v2 · level recorded 2026-09-22
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
models/MAT.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 9bf22d4f451ed68d · report fixture: returned Block · level recorded 2026-09-22
Conv2dDynamicSamePadding models/MAT.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · fac9df854d8f28ec · report fixture: returned Conv2dDynamicSamePadding · level recorded 2026-09-22
Conv2dStaticSamePadding in 5 papers models/MAT.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 1d6d41efbaa4e76e · report fixture: returned Conv2dStaticSamePadding · level recorded 2026-09-22
Identity in 49 papers
census: 10 implementations from 13 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
models/MAT.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 552d3aca78645318 · report fixture: returned Identity · level recorded 2026-09-22
MBConvBlock in 10 papers models/MAT.py ran · metamorphic tier: deterministic no licence file found · pointer only · 12770455a6977457 · report fixture: returned MBConvBlock · level recorded 2026-09-22
MemoryEfficientSwish models/MAT.py ran fingerprinted no licence file found · pointer only · 216a33b331a90731 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
SeparableConv2d in 5 papers models/MAT.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · e62c4554809ce2bc · report fixture: returned SeparableConv2d · level recorded 2026-09-22
Swish in 30 papers
census: 22 implementations from 19 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
models/MAT.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 0fb7ab180e596005 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
SwishImplementation models/MAT.py ran no licence file found · pointer only · 6fca2143a077d04e · report fixture: returned SwishImplementation · level recorded 2026-09-22
Texture_Enhance_v2 models/MAT.py ran no licence file found · pointer only · 8e7280a7aaf78ae0 · report fixture: signature feature_maps:Tensor/4/float, attention_maps:Tensor/4/float · returned tuple · level recorded 2026-09-24
drop_connect in 73 papers
census: 9 implementations from 7 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32
models/MAT.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 2dd5dfa94542911e · report fixture: signature inputs:Tensor/4/float, p:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22
efficientnet in 8 papers models/MAT.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 257c1c1e61218873 · report fixture: signature width_coefficient:float/0/float, depth_coefficient:float/0/float, dropout_rate:float/0/float, drop_connect_rate:float/0/float, image_size:int/0/int, num_classes:int/0/int · returned tuple · level recorded 2026-09-22
efficientnet_params in 9 papers models/MAT.py ran · honoured contract no licence file found · pointer only · 0d2081257b75b978 · report fixture: signature model_name:str/0/str · returned tuple · level recorded 2026-09-22
get_same_padding_conv2d in 6 papers models/MAT.py ran · our draft was wrong no licence file found · pointer only · 4c8a17dc9214affe · report fixture: signature image_size:NoneType/0/? · returned type · level recorded 2026-09-22
round_filters in 47 papers models/MAT.py ran · honoured contract no licence file found · pointer only · 826e2e91d6a9ec09 · report fixture: signature filters:int/0/int, global_params:GlobalParams/0/? · returned int · level recorded 2026-09-22
round_repeats in 39 papers models/MAT.py ran · honoured contract no licence file found · pointer only · 4d8e794b593d34a0 · report fixture: signature repeats:int/0/int, global_params:GlobalParams/0/? · returned int · level recorded 2026-09-22
xception in 13 papers models/MAT.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · a4916d92d14f412b · report fixture: returned xception · level recorded 2026-09-22
BlockDecoder models/MAT.py unverified no licence file found · pointer only · 43fa0c458613b03f · report
EfficientNet in 7 papers models/MAT.py unverified no licence file found · pointer only · 1bf7777ed9460905 · report
MAT models/MAT.py unverified no licence file found · pointer only · ed884b31a2f023a3 · report
get_model_params in 15 papers models/MAT.py unverified no licence file found · pointer only · 3872570123f9e3ae · report
load_pretrained_weights in 20 papers models/MAT.py unverified no licence file found · pointer only · 5545a1c79e2818b2 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for multi-attentional deepfake detection network (graph method: multi-attentional deepfake detection network). 25 bricks; individually on a fixture: 20 ran (of which 10 constructed an object rather than computing a result; 17 with no instrument failure: 3 honoured, 0 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. MAT entry · level 0 · unverified · ed884b31a2f023a3
  2. AttentionMap helper · level 1 · ran · 43d9801d323877e5
  3. AttentionPooling model · level 1 · ran · 020e1d7ced206b80
  4. Auxiliary_Loss_v2 loss · level 1 · ran · ee64f50e0c084ee1
  5. EfficientNet helper · level 0 · unverified · 1bf7777ed9460905
  6. Texture_Enhance_v2 model · level 1 · ran · 8e7280a7aaf78ae0
  7. xception helper · level 1 · ran · a4916d92d14f412b
  8. MBConvBlock helper · level 1 · ran · 12770455a6977457
  9. MemoryEfficientSwish helper · level 1 · ran · 216a33b331a90731
  10. Swish helper · level 1 · ran · 0fb7ab180e596005
  11. efficientnet_params helper · level 1 · ran · honoured contract · 0d2081257b75b978
  12. get_model_params helper · level 0 · unverified · 3872570123f9e3ae
  13. get_same_padding_conv2d helper · level 1 · ran · our draft was wrong · 4c8a17dc9214affe
  14. load_pretrained_weights helper · level 0 · unverified · 5545a1c79e2818b2
  15. round_filters helper · level 1 · ran · honoured contract · 826e2e91d6a9ec09
  16. round_repeats helper · level 1 · ran · honoured contract · 4d8e794b593d34a0
  17. Block helper · level 1 · ran · 9bf22d4f451ed68d
  18. SeparableConv2d helper · level 1 · ran · e62c4554809ce2bc
  19. drop_connect helper · level 1 · ran; the contract check could not run (RAISES) · 2dd5dfa94542911e
  20. SwishImplementation helper · level 1 · ran · 6fca2143a077d04e
  21. efficientnet helper · level 1 · ran · our draft was wrong · 257c1c1e61218873
  22. Conv2dDynamicSamePadding helper · level 1 · ran · fac9df854d8f28ec
  23. Conv2dStaticSamePadding helper · level 1 · ran · 1d6d41efbaa4e76e
  24. BlockDecoder helper · level 0 · unverified · 43fa0c458613b03f
  25. Identity helper · level 1 · ran · 552d3aca78645318

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2103.02406") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Binary ClassificationData AugmentationDeepFake DetectionFace Swapping

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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