Papers › Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection

Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection

4 Mar 2024arXiv:2403.01786archive 2025-07-28

Zhongjie Ba, Qingyu Liu, Zhenguang Liu, Shuang Wu, Feng Lin, Li Lu, Kui Ren

Deepfake technology has given rise to a spectrum of novel and compelling applications. Unfortunately, the widespread proliferation of high-fidelity fake videos has led to pervasive confusion and deception, shattering our faith that seeing is believing. One aspect that has been overlooked so far is that current deepfake detection approaches may easily fall into the trap of overfitting, focusing only on forgery clues within one or a few local regions. Moreover, existing works heavily rely on neural networks to extract forgery features, lacking theoretical constraints guaranteeing that sufficient forgery clues are extracted and superfluous features are eliminated. These deficiencies culminate in unsatisfactory accuracy and limited generalizability in real-life scenarios. In this paper, we try to tackle these challenges through three designs: (1) We present a novel framework to capture broader forgery clues by extracting multiple non-overlapping local representations and fusing them into a global semantic-rich feature. (2) Based on the information bottleneck theory, we derive Local Information Loss to guarantee the orthogonality of local representations while preserving comprehensive task-relevant information. (3) Further, to fuse the local representations and remove task-irrelevant information, we arrive at a Global Information Loss through the theoretical analysis of mutual information. Empirically, our method achieves state-of-the-art performance on five benchmark datasets.Our code is available at https://github.com/QingyuLiu/Exposing-the-Deception, hoping to inspire researchers.

PaperPDFCodeCode 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: 17 ran (of which 7 constructed an object rather than computing a result; 13 with no instrument failure: 4 honoured, 0 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 3 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, 17 ran (13 with no instrument failure; 4 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.

qingyuliu/exposing-the-deception officialmentioned in paperpytorchSyntology: 25 samples, 17 ran (4 instrument-failed) · 8 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: 17 ran (of which 7 constructed an object rather than computing a result; 13 with no instrument failure: 4 honoured, 0 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 8 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
3ran · our draft was wrong
1ran; the contract check could not run
9ran
8unverified

Licence: 0 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 qingyuliu/exposing-the-deception. “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 6 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.

qingyuliu/exposing-the-deception official repository 25 samples, 17 ran (4 instrument-failed) · 8 unverified
BlockDecoder models/MI_Net.py ran Apache-2.0 (permissive) · 3e5ed67f701eca85 · report fixture: signature string_list:list/1/str · returned list · level recorded 2026-09-24
ChannelCompress models/MI_Net.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 04529829360d2bee · report fixture: returned ChannelCompress · level recorded 2026-09-22
Conv2dDynamicSamePadding models/MI_Net.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · f5a0e3d9dd9e1f9f · report fixture: returned Conv2dDynamicSamePadding · level recorded 2026-09-22
Conv2dStaticSamePadding in 5 papers models/MI_Net.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 6b6a8511b4a4c914 · report fixture: returned Conv2dStaticSamePadding · level recorded 2026-09-22
MBConvBlock in 10 papers models/MI_Net.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 22224e6f538dca75 · report fixture: returned MBConvBlock · level recorded 2026-09-22
MemoryEfficientSwish models/MI_Net.py ran fingerprinted Apache-2.0 (permissive) · dfd0461ebe45d041 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
MobileNetV1 models/MI_Net.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · a10be7ad329fa289 · report fixture: returned MobileNetV1 · level recorded 2026-09-22
ResNet in 139 papers models/MI_Net.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 46379fc15f2ee62a · report fixture: returned ResNet · level recorded 2026-09-22
SwishImplementation models/MI_Net.py ran Apache-2.0 (permissive) · 64a011654b82d503 · report fixture: returned SwishImplementation · level recorded 2026-09-22
calculate_output_image_size in 9 papers models/MI_Net.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 1463b46fb531ddac · report fixture: signature input_image_size:int/0/int, stride:int/0/int · returned list · level recorded 2026-09-22
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/MI_Net.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · d3319e3d34ca90ca · report fixture: signature inputs:Tensor/4/float, p:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22
efficientnet_params in 9 papers models/MI_Net.py ran · honoured contract Apache-2.0 (permissive) · 158895ccad37077c · report fixture: signature model_name:str/0/str · returned tuple · level recorded 2026-09-22
get_output_size models/MI_Net.py ran · honoured contract Apache-2.0 (permissive) · 57cafea17f72df42 · report fixture: signature net:callable/0/? · returned int · level recorded 2026-09-22
get_same_padding_conv2d in 6 papers models/MI_Net.py ran · our draft was wrong Apache-2.0 (permissive) · ecd5b19163cc5430 · report fixture: signature image_size:NoneType/0/? · returned type · level recorded 2026-09-22
get_width_and_height_from_size in 10 papers models/MI_Net.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · ed9d02b76fb84ae4 · report fixture: signature x:int/0/int · returned tuple · level recorded 2026-09-22
round_filters in 47 papers models/MI_Net.py ran · our draft was wrong Apache-2.0 (permissive) · f15a49337e69e937 · report fixture: signature filters:int/0/int, global_params:GlobalParams/1/float · returned int · level recorded 2026-09-22
round_repeats in 39 papers models/MI_Net.py ran · our draft was wrong Apache-2.0 (permissive) · dbc0ca08d119a5a0 · report fixture: signature repeats:int/0/int, global_params:GlobalParams/1/float · returned int · level recorded 2026-09-22
EfficientNet in 7 papers models/MI_Net.py unverified Apache-2.0 (permissive) · 26488aa7fc70e759 · report
MI_Net models/MI_Net.py unverified Apache-2.0 (permissive) · 380bef540fcd9569 · report
_resnet in 27 papers models/MI_Net.py unverified Apache-2.0 (permissive) · 9c43e20a92c08bf4 · report
efficientnet in 8 papers models/MI_Net.py unverified Apache-2.0 (permissive) · 7c07cd76854d45e9 · report
freeze in 9 papers models/MI_Net.py unverified Apache-2.0 (permissive) · 30090882dbaf19ed · report
get_model_params in 15 papers models/MI_Net.py unverified Apache-2.0 (permissive) · c58da27c524ad799 · report
load_pretrained_weights in 20 papers models/MI_Net.py unverified Apache-2.0 (permissive) · d930abcc85af042c · report
resnet34 in 148 papers models/MI_Net.py unverified Apache-2.0 (permissive) · 2db125f45811942f · 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 novel framework (graph method: novel framework). 29 bricks; individually on a fixture: 21 ran (of which 9 constructed an object rather than computing a result; 15 with no instrument failure: 4 honoured, 0 violated, 11 with no contract checked; 6 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.

  1. MI_Net entry · level 0 · unverified · 380bef540fcd9569
  2. ChannelCompress model · level 1 · ran · 04529829360d2bee
  3. EfficientNet helper · level 0 · unverified · 26488aa7fc70e759
  4. MobileNetV1 helper · level 1 · ran · a10be7ad329fa289
  5. freeze helper · level 0 · unverified · 30090882dbaf19ed
  6. get_output_size helper · level 1 · ran · honoured contract · 57cafea17f72df42
  7. resnet34 helper · level 0 · unverified · 2db125f45811942f
  8. MBConvBlock helper · level 1 · ran · 22224e6f538dca75
  9. MemoryEfficientSwish helper · level 1 · ran · dfd0461ebe45d041
  10. calculate_output_image_size helper · level 1 · ran · honoured contract · 1463b46fb531ddac
  11. efficientnet_params helper · level 1 · ran · honoured contract · 158895ccad37077c
  12. get_model_params helper · level 0 · unverified · c58da27c524ad799
  13. get_same_padding_conv2d helper · level 1 · ran · our draft was wrong · ecd5b19163cc5430
  14. load_pretrained_weights helper · level 0 · unverified · d930abcc85af042c
  15. round_filters helper · level 1 · ran · our draft was wrong · f15a49337e69e937
  16. round_repeats helper · level 1 · ran · our draft was wrong · dbc0ca08d119a5a0
  17. BasicBlock helper · level 1 · ran · d42ae3fd7fcd5024
  18. ResNet helper · level 1 · ran · 46379fc15f2ee62a
  19. _resnet helper · level 0 · unverified · 9c43e20a92c08bf4
  20. drop_connect helper · level 1 · ran; the contract check could not run (RAISES) · d3319e3d34ca90ca
  21. SwishImplementation helper · level 1 · ran · 64a011654b82d503
  22. get_width_and_height_from_size helper · level 1 · ran · honoured contract · ed9d02b76fb84ae4
  23. efficientnet helper · level 0 · unverified · 7c07cd76854d45e9
  24. Conv2dDynamicSamePadding helper · level 1 · ran · f5a0e3d9dd9e1f9f
  25. Conv2dStaticSamePadding helper · level 1 · ran · 6b6a8511b4a4c914
  26. conv3x3 helper · level 1 · ran · our draft was wrong · 600ff2c45e0de056
  27. Bottleneck helper · level 1 · ran · 6d8a817f41286a76
  28. conv1x1 helper · level 1 · ran · our draft was wrong · 2a80220dabcb742a
  29. BlockDecoder helper · level 1 · ran · 3e5ed67f701eca85

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="2403.01786") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DeepFake 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