SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.03262 · 2023

Membership Inference Attacks against Diffusion Models

arXiv · PDF · Open in the Atlas

Code that ran

11 of 14 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 4 have no contract verdict; 6 failures of our instrument; 3 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/2302.03262.json · badge: /api/ran/2302.03262.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
fseclab-osaka/mia-diffusion canonical (classifier label)
classifier basis not recorded on the link
11 ran · 3 no recorded run
FunctionStatusWhere it lives
Normalize Ran
ran; our contract draft was wrong, not the code
fseclab-osaka/mia-diffusion/ddim/models/diffusion.py
pointer only (licence: MIT); the stored copy get_code serves, from Xingyu-Zheng/BiDM, is pointer only (licence: NONE) · get_code("c3a6b977022957cb")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Xingyu-Zheng/BiDM, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

betas_for_alpha_bar Ran
ran, honoured the contract we drafted
fseclab-osaka/mia-diffusion/ddim/runners/diffusion.py
code served (permissive licence) · get_code("7eb19b2d745af94f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned ndarray, ndim 1, dtype family float, shape (10,) 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

def alpha_bar_cosine(t):
    """Cosine schedule for alpha_bar"""
    return np.cos((t + 0.008) / 1.008 * np.pi / 2) ** 2

ARGS = {
    "num_diffusion_timesteps": 10,
    "alpha_bar": alpha_bar_cosine,
    "max_beta": 0.999
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (10,) — shape (10,) 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
calculate_frechet_distance Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fseclab-osaka/mia-diffusion/TTUR/fid.py
code served (permissive licence) · get_code("5277c96076ea2fe5")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned float64, ndim 0, dtype family float, shape () 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

np.random.seed(42)

# Create mean vectors for two distributions
# Using different dimensions to make them distinct
feature_dim = 128

mu1 = np.random.randn(feature_dim)
mu2 = np.random.randn(feature_dim)

# Create covariance matrices (must be positive semi-definite)
# Generate random covariance matrices by A @ A.T method
A1 = np.random.randn(feature_dim, feature_dim)
sigma1 = A1 @ A1.T

A2 = np.random.randn(feature_dim, feature_dim)
sigma2 = A2 @ A2.T

eps = 1e-06

ARGS = {
    'mu1': mu1,
    'sigma1': sigma1,
    'mu2': mu2,
    'sigma2': sigma2,
    'eps': eps
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float, shape () — shape () 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
find_knn Ran
ran on a synthesized input
fseclab-osaka/mia-diffusion/attacks/fbb.py
code served (permissive licence) · get_code("4b55cf9a5ba8cdfc")
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 tuple, ndim 3, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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
from sklearn.neighbors import NearestNeighbors

# Create a mock nearest neighbor object
nn_obj = NearestNeighbors(n_neighbors=5)

# Create mock training data for the KNN model to fit on
# Shape: (100, 12) - 100 samples, each flattened to 12 dimensions
training_data = np.random.randn(100, 12).astype(np.float32)
nn_obj.fit(training_data)

# Create mock query data loader
# Each batch is a tuple of (x_batch, y_batch)
# x_batch shape: (100, 3, 4) - will be reshaped to (100, 12)
# y_batch: dummy labels
query_imgs = [
    (np.random.randn(100, 3, 4).astype(np.float32), np.zeros(100)),
    (np.random.randn(100, 3, 4).astype(np.float32), np.zeros(100)),
]

ARGS = {
    "nn_obj": nn_obj,
    "query_imgs": query_imgs,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 3, dtype family float — a tuple output has no array shape of its own; none is stated
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
find_pred_z Ran
ran on a synthesized input
fseclab-osaka/mia-diffusion/attacks/fbb.py
code served (permissive licence) · get_code("4163c565f0a353d8")
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 3, dtype family float, shape (2, 5, 4) 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

# K is defined globally in the module as 5
K = 5

# Analyze what find_pred_z expects:
# - gen_z: needs to be indexable, should contain latent codes
# - idx: needs to be a 2D array-like with shape (num_samples, K)
#   where idx[i, nn] accesses the index for sample i and neighbor nn

# Create small example data
# gen_z: array of latent codes, shape (10, 4) - 10 samples with 4-dim latent codes
gen_z = np.random.randn(10, 4).astype(np.float32)

# idx: array of shape (2, 5) - 2 samples, 5 neighbors each
# Each entry should be a valid index into gen_z (0-9)
idx = np.array([
    [0, 1, 2, 3, 4],
    [5, 6, 7, 8, 9]
], dtype=np.int32)

ARGS = {
    "gen_z": gen_z,
    "idx": idx
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family float, shape (2, 5, 4) — shape (2, 5, 4) 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
get_beta_schedule Ran
ran on a synthesized input
fseclab-osaka/mia-diffusion/ddim/runners/diffusion.py
code served (permissive licence) · get_code("70a7a36a723cc519")
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 1, dtype family float, shape (1000,) 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 math

ARGS = {
    'beta_schedule': 'cosine',
    'beta_start': 0.0001,
    'beta_end': 0.02,
    'num_diffusion_timesteps': 1000
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (1000,) — shape (1000,) 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
get_dataloader_cifar10 Ran
ran on a synthesized input
fseclab-osaka/mia-diffusion/mydataset.py
code served (permissive licence) · get_code("cd5c81bb93d0f22a")
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 tuple. The image it ran in was not recorded. If your copy returns the same type 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 os
import torch
import numpy as np
import tempfile
import shutil
from unittest.mock import MagicMock, patch
import torchvision.transforms as transforms
from torchvision.datasets import CIFAR10
from torch.utils.data import DataLoader, TensorDataset, Subset

torch.manual_seed(0)
np.random.seed(0)

# Create a minimal mock dataset that behaves like CIFAR10
class MockCIFAR10(TensorDataset):
    def __init__(self, train=True, transform=None):
        # Create dummy data: 50000 samples of 3x32x32 images with labels
        num_samples = 50000
        images = torch.randint(0, 256, (num_samples, 3, 32, 32), dtype=torch.uint8)
        labels = torch.randint(0, 10, (num_samples,))
        super().__init__(images, labels)
        self.transform = transform
    
    def __getitem__(self, idx):
        img, label = super().__getitem__(idx)
        if self.transform:
            img = self.transform(img)
        return img, label

# Patch CIFAR10 to use our mock
original_cifar10 = CIFAR10

def mock_cifar10_init(self, root, train=True, download=False, transform=None):
    mock_dataset = MockCIFAR10(train=train, transform=transform)
    self.data = mock_dataset.tensors[0]
    self.targets = mock_dataset.tensors[1]
    self.transform = transform
    self.train = train

CIFAR10.__init__ = mock_cifar10_init
CIFAR10.__getitem__ = lambda self, idx: (self.data[idx], self.targets[idx]) if self.transform is None else (self.transform(self.data[idx]), self.targets[idx])
CIFAR10.__len__ = lambda self: len(self.data)

ARGS = {
    "image_size": 32,
    "batch_size": 4,
    "num_data": 100,
    "seed": 42,
    "normalize": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
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
get_timestep_embedding Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fseclab-osaka/mia-diffusion/ddim/models/diffusion.py
code served (permissive licence) · get_code("cb49209c125de1b4")
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) and returned Tensor, ndim 2, dtype family float, shape (2, 4) 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 torch
import math

torch.manual_seed(0)

# The function takes two parameters:
# 1. timesteps: a 1D tensor of timestep indices
# 2. embedding_dim: an integer specifying the embedding dimension

# Create a small 1D tensor of timesteps (batch size 2)
timesteps = torch.tensor([0, 5], dtype=torch.int64)

# Create an embedding dimension (use 4 as specified)
embedding_dim = 4

ARGS = {
    "timesteps": timesteps,
    "embedding_dim": embedding_dim,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
noise_estimation_loss Ran
ran; our contract draft was wrong, not the code
fseclab-osaka/mia-diffusion/ddim/functions/losses.py
code served (permissive licence) · get_code("36a45cceb1209d2f")
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 Tensor, ndim 0, dtype family float, shape () 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Define a simple model that takes (x, t) and outputs noise prediction
class NoisePredictor(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 4)
    
    def forward(self, x, t):
        # x shape: (batch, channels, height, width) = (2, 1, 1, 4)
        # t shape: (batch,) converted to float
        # output should match x shape
        batch_size = x.shape[0]
        x_flat = x.view(batch_size, -1)
        # t is (batch,), expand it to match
        t_expanded = t.unsqueeze(1)  # (batch, 1)
        combined = x_flat + t_expanded  # simple combination
        output = self.linear(combined)
        return output.view(batch_size, 1, 1, 4)

model = NoisePredictor()

# x0: original clean image, shape (batch=2, channels=1, height=1, width=4)
x0 = torch.randn(2, 1, 1, 4)

# t: timesteps, shape (batch=2,)
t = torch.LongTensor([0, 5])

# e: noise, same shape as x0
e = torch.randn(2, 1, 1, 4)

# b: betas (noise schedule), shape (num_timesteps,) - needs at least 6 elements for index 5
b = torch.linspace(0.0001, 0.02, 10)

ARGS = {
    "model": model,
    "x0": x0,
    "t": t,
    "e": e,
    "b": b,
    "keepdim": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () 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
nonlinearity Ran
ran; our contract draft was wrong, not the code
fseclab-osaka/mia-diffusion/ddim/models/diffusion.py
code served (permissive licence) · get_code("3137073275f8c21a")
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) and returned Tensor, ndim 2, dtype family float, shape (2, 4) 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 torch

torch.manual_seed(0)

# The function takes a single parameter 'x' which is used with:
# - multiplication operator (*)
# - torch.sigmoid() function
# This means x should be a tensor

x = torch.randn(2, 4)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
torch2hwcuint8 Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fseclab-osaka/mia-diffusion/ddim/runners/diffusion.py
pointer only (licence: MIT); the stored copy get_code serves, from weizhigao/modiff, is pointer only (licence: NONE) · get_code("c27a10ca9f6b75f3")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from weizhigao/modiff, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

calculate_activation_statistics Not yet run
unverified (harvested, no recorded run)
fseclab-osaka/mia-diffusion/TTUR/fid.py
code served (permissive licence) · get_code("2dff109c7a95321a")
How it ran

no invocation recorded.

get_activations Not yet run
unverified (harvested, no recorded run)
fseclab-osaka/mia-diffusion/TTUR/fid.py
code served (permissive licence) · get_code("1b7fb683b1a517bc")
How it ran

no invocation recorded.

get_dataloader_celeba Not yet run
unverified (harvested, no recorded run)
fseclab-osaka/mia-diffusion/mydataset.py
code served (permissive licence) · get_code("dad3a4c772ca2124")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 8 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 3 the same month, 8 later) and 6 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
nonlinearity 156 other papers
23 dated earlier, 1 the same month, 131 later, 1 same year, order not determinable · 25 only as an assembly brick
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
2106.00132 (2021-06)
On Fast Sampling of Diffusion Probabilistic Models
2106.06819 (2021-06)
D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
and 153 more not named here
betas_for_alpha_bar 92 other papers
30 dated earlier, 1 the same month, 59 later, 2 same year, order not determinable · 3 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2102.09672 (2021-02)
Improved Denoising Diffusion Probabilistic Models
and 89 more not named here
get_timestep_embedding 91 other papers
19 dated earlier, 71 later, 1 same year, order not determinable · 7 only as an assembly brick
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
2106.00132 (2021-06)
On Fast Sampling of Diffusion Probabilistic Models
2106.06819 (2021-06)
D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
and 88 more not named here
Normalize 90 other papers
17 dated earlier, 1 the same month, 72 later · 32 only as an assembly brick
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
2106.00132 (2021-06)
On Fast Sampling of Diffusion Probabilistic Models
2106.06819 (2021-06)
D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
and 87 more not named here
calculate_frechet_distance 15 other papers
12 dated earlier, 3 later
1406.2661 (2014-06)
Generative Adversarial Networks
1703.10593 (2017-03)
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
1706.08500 (2017-06)
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
and 12 more not named here
noise_estimation_loss 14 other papers
4 dated earlier, 10 later
2106.06819 (2021-06)
D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
2206.02262 (2022-06)
Diffusion-GAN: Training GANs with Diffusion
2211.14680 (2022-11)
A Physics-informed Diffusion Model for High-fidelity Flow Field Reconstruction
and 11 more not named here
calculate_activation_statistics 12 other papers
10 dated earlier, 2 later
1406.2661 (2014-06)
Generative Adversarial Networks
1703.10593 (2017-03)
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
1710.10196 (2017-10)
Progressive Growing of GANs for Improved Quality, Stability, and Variation
and 9 more not named here
torch2hwcuint8 5 other papers
2 dated earlier, 3 later
2206.02262 (2022-06)
Diffusion-GAN: Training GANs with Diffusion
2211.14680 (2022-11)
A Physics-informed Diffusion Model for High-fidelity Flow Field Reconstruction
2305.18723 (2023-05)
Towards Accurate Post-training Quantization for Diffusion Models
and 2 more not named here

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

Diffusion models have attracted attention in recent years as innovative generative models. In this paper, we investigate whether a diffusion model is resistant to a membership inference attack, which evaluates the privacy leakage of a machine learning model. We primarily discuss the diffusion model from the standpoints of comparison with a generative adversarial network (GAN) as conventional models and hyperparameters unique to the diffusion model, i.e., time steps, sampling steps, and sampling variances. We conduct extensive experiments with DDIM as a diffusion model and DCGAN as a GAN on the CelebA and CIFAR-10 datasets in both white-box and black-box settings and then confirm if the diffusion model is comparably resistant to a membership inference attack as GAN. Next, we demonstrate that the impact of time steps is significant and intermediate steps in a noise schedule are the most vulnerable to the attack. We also found two key insights through further analysis. First, we identify that DDIM is vulnerable to the attack for small sample sizes instead of achieving a lower FID. Second, sampling steps in hyperparameters are important for resistance to the attack, whereas the impact of sampling variances is quite limited.

For agents

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

get_harvested_code_for_paper("2302.03262")
get_code_for_paper("2302.03262")
have("2302.03262")

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

curl https://syntology.ai/api/ran/2302.03262.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.03262.svg)](https://syntology.ai/paper/2302.03262)

Connect an agent — have() is free.