SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1809.00888 · 2018

MesoNet: a Compact Facial Video Forgery Detection Network

arXiv · PDF · Open in the Atlas

Code that ran

1 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 0 failures of our instrument; 5 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1809.00888.json · badge: /api/ran/1809.00888.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
DariusAf/MesoNet canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
Raj-08/Deepfake-Detection-Mesonet community (classifier label)
classifier basis not recorded on the link
0 ran · 5 no recorded run
FunctionStatusWhere it lives
predict_faces Ran
ran, honoured the contract we drafted
DariusAf/MesoNet/pipeline.py
code served (permissive licence) · get_code("7f4585435158da77")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (10, 1) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import torch
import torch.nn as nn

torch.manual_seed(0)

# Stand-in class for the finder with coordinates
class Finder:
    def __init__(self, num_coordinates):
        self.coordinates = {i: (i, i) for i in range(num_coordinates)}

# Stand-in generator class
class Generator:
    def __init__(self, num_coordinates=10):
        self.finder = Finder(num_coordinates)
        self.batch_counter = 0
        self.num_coordinates = num_coordinates
    
    def next_batch(self, batch_size=50):
        # Return a batch of face data (numpy array)
        # Output should be compatible with classifier.predict
        actual_batch_size = min(batch_size, self.num_coordinates - self.batch_counter)
        if actual_batch_size <= 0:
            return np.array([]).reshape(0, 4)
        batch = np.random.randn(actual_batch_size, 4)
        self.batch_counter += actual_batch_size
        return batch

# Stand-in classifier class
class Classifier(nn.Module):
    def __init__(self, input_size=4, output_size=1):
        super().__init__()
        self.linear = nn.Linear(input_size, output_size)
    
    def predict(self, face_batch):
        # face_batch is a numpy array
        if len(face_batch) == 0:
            return np.array([]).reshape(0, 1)
        tensor = torch.from_numpy(face_batch).float()
        with torch.no_grad():
            output = self.linear(tensor)
        return output.numpy()

# Create instances
generator = Generator(num_coordinates=10)
classifier = Classifier(input_size=4, output_size=1)

ARGS = {
    "generator": generator,
    "classifier": classifier,
    "batch_size": 3,
    "output_size": 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (10, 1) — shape (10, 1) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
bias_variable Not yet run
unverified (harvested, no recorded run)
Raj-08/Deepfake-Detection-Mesonet/ops.py
code served (permissive licence) · get_code("d76e69553bdf6bda")
How it ran

no invocation recorded.

fc_layer Not yet run
unverified (harvested, no recorded run)
Raj-08/Deepfake-Detection-Mesonet/ops.py
code served (permissive licence) · get_code("0ee136663cdae137")
How it ran

no invocation recorded.

random_crop_and_pad_image Not yet run
unverified (harvested, no recorded run)
Raj-08/Deepfake-Detection-Mesonet/utils.py
code served (permissive licence) · get_code("78742eea751f0f2b")
How it ran

no invocation recorded.

random_crop_and_pad_image_and_labels Not yet run
unverified (harvested, no recorded run)
Raj-08/Deepfake-Detection-Mesonet/utils.py
code served (permissive licence) · get_code("412d3f5558dc4f31")
How it ran

no invocation recorded.

weight_variable Not yet run
unverified (harvested, no recorded run)
Raj-08/Deepfake-Detection-Mesonet/ops.py
code served (permissive licence) · get_code("9c44b685b4a9551a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 1 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
bias_variable 3 other papers
1 dated earlier, 2 later
1607.07539 (2016-07)
Semantic Image Inpainting with Deep Generative Models
1906.04569 (2019-06)
DropConnect Is Effective in Modeling Uncertainty of Bayesian Deep Networks
2008.05770 (2020-08)
Weakly Supervised Generative Network for Multiple 3D Human Pose Hypotheses
random_crop_and_pad_image 1 other paper
1 dated earlier
1603.04530 (2016-03)
Object Contour Detection with a Fully Convolutional Encoder-Decoder Network
weight_variable 1 other paper
1 dated earlier
1607.07539 (2016-07)
Semantic Image Inpainting with Deep Generative Models

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

This paper presents a method to automatically and efficiently detect face tampering in videos, and particularly focuses on two recent techniques used to generate hyper-realistic forged videos: Deepfake and Face2Face. Traditional image forensics techniques are usually not well suited to videos due to the compression that strongly degrades the data. Thus, this paper follows a deep learning approach and presents two networks, both with a low number of layers to focus on the mesoscopic properties of images. We evaluate those fast networks on both an existing dataset and a dataset we have constituted from online videos. The tests demonstrate a very successful detection rate with more than 98% for Deepfake and 95% for Face2Face.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1809.00888")
get_code_for_paper("1809.00888")
have("1809.00888")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1809.00888.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1809.00888.svg)](https://syntology.ai/paper/1809.00888)

Connect an agent — have() is free.