SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2201.12179 · ICML · 2022

Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks

Kristian Kersting, Lukas Struppek, Dominik Hintersdorf, Antonio De Almeida Correia, Antonia Adler

arXiv · PDF · Open in the Atlas

Code that ran

27 of 36 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 2 violated it and 4 have no contract verdict; 20 failures of our instrument; 9 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/2201.12179.json · badge: /api/ran/2201.12179.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
ajbrock/BigGAN-PyTorch canonical (classifier label)
classifier basis not recorded on the link
18 ran · 2 no recorded run
lukasstruppek/plug-and-play-attacks canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
AI-secure/GMI-Attack community
Papers with Code archive
3 ran · 1 no recorded run
SCccc21/Knowledge-Enriched-DMI community
Papers with Code archive
1 ran · 5 no recorded run
LukasStruppek/Plug-and-Play-Attacks marked official in Papers with Code
Papers with Code archive
1 ran · 1 no recorded run
wangkua1/vmi unrelated (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
lukasstruppek/class_attribute_inference_attacks community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
ContextNetwork Ran
ran on a synthesized input
AI-secure/GMI-Attack/Celeba/generator.py
pointer only (licence: NONE) · get_code("390270b249117165")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AI-secure/GMI-Attack 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.

D_arch Ran
ran; our contract draft was wrong, not the code
ajbrock/BigGAN-PyTorch/BigGAN.py
pointer only (licence: MIT); the stored copy get_code serves, from VICO-UoE/IT-GAN, is pointer only (licence: NONE) · get_code("85eb95cce203dfc7")
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 VICO-UoE/IT-GAN, 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.

D_arch Ran
ran; our contract draft was wrong, not the code
ajbrock/BigGAN-PyTorch/BigGANdeep.py
code served (permissive licence) · get_code("a99a05ac52533be9")
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 dict. 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 torch
import numpy as np

torch.manual_seed(0)

ARGS = {
    'ch': 64,
    'attention': '64',
    'ksize': '333333',
    'dilation': '111111'
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
G_arch Ran
ran; our contract draft was wrong, not the code
ajbrock/BigGAN-PyTorch/BigGAN.py
pointer only (licence: MIT); the stored copy get_code serves, from VICO-UoE/IT-GAN, is pointer only (licence: NONE) · get_code("e8c308c9283407d7")
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 VICO-UoE/IT-GAN, 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.

G_arch Ran
ran; our contract draft was wrong, not the code
ajbrock/BigGAN-PyTorch/BigGANdeep.py
code served (permissive licence) · get_code("44d6a6343f6eb182")
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 dict. 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 torch
import numpy as np

torch.manual_seed(0)

ARGS = {
    'ch': 64,
    'attention': '64_128_256',
    'ksize': '333333',
    'dilation': '111111'
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
IdentityGenerator Ran
ran on a synthesized input
AI-secure/GMI-Attack/Celeba/generator.py
pointer only (licence: NONE) · get_code("29f3f93ece1d2af8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AI-secure/GMI-Attack 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.

MineGAN Ran
ran on a synthesized input · constructed an object; no result was computed
wangkua1/vmi/attack_stylegan.py
pointer only (licence: NONE) · get_code("3a4c1d8b783d177b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wangkua1/vmi 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.

create_image Ran
ran; our contract draft was wrong, not the code
lukasstruppek/class_attribute_inference_attacks/attack_ppa.py
code served (permissive licence) · get_code("b4f439c13b63055d")
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 4, dtype family float, shape (2, 3, 48, 48) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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
import math

torch.manual_seed(0)

# Create a minimal generator mock that satisfies the function's usage
class MinimalGenerator(nn.Module):
    def __init__(self, num_ws=8):
        super().__init__()
        self.num_ws = num_ws
    
    def forward(self, w_batch, noise_mode='const', force_fp32=True):
        # w_batch shape: (batch_size, num_ws, latent_dim)
        # Return generated images of shape (batch_size, 3, 64, 64)
        batch_size = w_batch.shape[0]
        return torch.randn(batch_size, 3, 64, 64)

# Create generator instance
generator = MinimalGenerator(num_ws=8)

# Create w tensor with shape (2, 1, 512) - batch_size=2, single w vector, latent_dim=512
w = torch.randn(2, 1, 512)

# Define all arguments
ARGS = {
    'w': w,
    'generator': generator,
    'crop_size': 32,
    'resize': 48,
    'batch_size': 20,
    'device': 'cpu'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 3, 48, 48) — shape (2, 3, 48, 48) 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
create_initial_vectors Ran
ran; our contract draft was wrong, not the code
lukasstruppek/plug-and-play-attacks/attack.py
code served (permissive licence) · get_code("fa4ee3a3e0b099a5")
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 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 torch
import torch.nn as nn
from copy import deepcopy

torch.manual_seed(0)

# Create a minimal config class with the required methods and attributes
class MinimalConfig:
    def __init__(self):
        self.attack = {'single_w': False}
    
    def create_candidates(self, G, target_model, targets):
        # Returns a tensor of shape (batch_size, num_candidates, ...)
        # We'll return shape (2, 3, 4) - batch=2, candidates=3, dim=4
        return torch.randn(2, 3, 4)

# Create a minimal target model
class MinimalTargetModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 2)
    
    def forward(self, x):
        return self.linear(x)

# Create minimal G (generator or similar)
class MinimalG(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 4)
    
    def forward(self, x):
        return self.linear(x)

# Instantiate objects
config = MinimalConfig()
G = MinimalG()
target_model = MinimalTargetModel()
targets = torch.randn(2, 2)  # batch_size=2, output_dim=2
device = torch.device('cpu')

ARGS = {
    'config': config,
    'G': G,
    'target_model': target_model,
    'targets': targets,
    'device': device
}
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 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
dconv_bn_relu Ran
ran; our contract draft was wrong, not the code
AI-secure/GMI-Attack/Celeba/generator.py
pointer only (licence: NONE) · get_code("17b094c69aebe5ed")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AI-secure/GMI-Attack 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.

denorm Ran
ran; our contract draft was wrong, not the code
ajbrock/BigGAN-PyTorch/TFHub/biggan_v1.py
code served (permissive licence) · get_code("6e16337c88174e00")
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 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 denorm takes a tensor x, applies (x + 1) / 2, and clamps to [0, 1]
# We need to provide a tensor that works with these operations

x = torch.randn(2, 4)

ARGS = {
    "x": x
}
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 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
find_classes Ran
ran; our contract draft was wrong, not the code
ajbrock/BigGAN-PyTorch/datasets.py
code served (permissive licence) · get_code("52d10a10fb72fb9f")
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 tempfile
import shutil

# Create a temporary directory with some subdirectories to simulate a class directory structure
temp_dir = tempfile.mkdtemp()
os.makedirs(os.path.join(temp_dir, "class_a"), exist_ok=True)
os.makedirs(os.path.join(temp_dir, "class_b"), exist_ok=True)
os.makedirs(os.path.join(temp_dir, "class_c"), exist_ok=True)

ARGS = {
    "dir": temp_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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_deprocessor Ran
ran on a synthesized input
SCccc21/Knowledge-Enriched-DMI/attack.py
code served (permissive licence) · get_code("d8f4bcdc2662ccd8")
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 Compose. 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 torch
import torch.nn as nn
from torchvision import transforms

torch.manual_seed(0)

# The function get_deprocessor() takes no parameters
# It simply constructs and returns a transforms.Compose object
# No arguments are needed to call this function

ARGS = {}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Compose — a Compose output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Compose output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
gram_schmidt Ran
ran; our contract draft was wrong, not the code
ajbrock/BigGAN-PyTorch/layers.py
pointer only (licence: MIT); the stored copy get_code serves, from mshahbazi72/cGANTransfer, is pointer only (licence: NONE) · get_code("c41836f3e51fa8f1")
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 mshahbazi72/cGANTransfer, 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.

is_image_file Ran
ran, violated the contract we drafted
ajbrock/BigGAN-PyTorch/datasets.py
pointer only (licence: MIT); the stored copy get_code serves, from ermongroup/fairgen, is pointer only (licence: NONE) · get_code("4e6a8faaf8e44abe")
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 ermongroup/fairgen, 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.

l2normalize Ran
ran, violated the contract we drafted
ajbrock/BigGAN-PyTorch/TFHub/biggan_v1.py
code served (permissive licence) · get_code("9b11458d7d1ec61c")
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 1, dtype family float, shape (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 l2normalize takes a vector v and normalizes it by dividing by its norm + eps
# v needs to be a torch tensor with a .norm() method
# eps is a small float for numerical stability

v = torch.randn(4)

ARGS = {
    "v": v,
    "eps": 0.0001
}
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 1, dtype family float, shape (4,) — shape (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
loss_dcgan_dis Ran
ran; our contract draft was wrong, not the code
ajbrock/BigGAN-PyTorch/losses.py
code served (permissive licence) · get_code("982a26492dc6b7fb")
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 1, 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 torch
import torch.nn.functional as F

torch.manual_seed(0)

# Create small discriminator output tensors
# dis_fake: discriminator output for fake samples
dis_fake = torch.randn(2, 4)

# dis_real: discriminator output for real samples
dis_real = torch.randn(2, 4)

ARGS = {
    "dis_fake": dis_fake,
    "dis_real": dis_real,
}
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 tuple, ndim 1, 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
loss_dcgan_gen Ran
ran; our contract draft was wrong, not the code
ajbrock/BigGAN-PyTorch/losses.py
code served (permissive licence) · get_code("6c34831223553b6f")
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.functional as F

torch.manual_seed(0)

# The function loss_dcgan_gen expects dis_fake, which is used with:
# - F.softplus() - expects a tensor
# - torch.mean() - expects a tensor
# So dis_fake should be a tensor

# Create a small fake discriminator output tensor (batch_size=2, some features)
dis_fake = torch.randn(2, 4)

ARGS = {
    "dis_fake": dis_fake,
}
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
loss_hinge_dis Ran
ran; our contract draft was wrong, not the code
ajbrock/BigGAN-PyTorch/losses.py
code served (permissive licence) · get_code("290cd37ab0098d5c")
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 1, 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 torch
import torch.nn.functional as F

torch.manual_seed(0)

# The function loss_hinge_dis takes two tensor arguments:
# dis_fake and dis_real
# It computes relu-based hinge losses on them and returns a tuple of two scalars

# Create small discriminator output tensors (batch_size=2, arbitrary values)
dis_fake = torch.randn(2, 4)  # Fake discriminator scores
dis_real = torch.randn(2, 4)  # Real discriminator scores

ARGS = {
    "dis_fake": dis_fake,
    "dis_real": dis_real,
}
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 tuple, ndim 1, 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
make_dataset Ran
ran; our contract draft was wrong, not the code
ajbrock/BigGAN-PyTorch/datasets.py
pointer only (licence: MIT); the stored copy get_code serves, from ermongroup/fairgen, is pointer only (licence: NONE) · get_code("79e61b6269a450e8")
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 ermongroup/fairgen, 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.

numpy_calculate_frechet_distance Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ajbrock/BigGAN-PyTorch/inception_utils.py
code served (permissive licence) · get_code("54af0200eab3163f")
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 float64, ndim 0, 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

# Set random seed for reproducibility
np.random.seed(0)

# Create small test data for Frechet Distance calculation
# mu1 and mu2 are mean vectors (1D arrays)
mu1 = np.array([0.1, 0.2, 0.3, 0.4])
mu2 = np.array([0.15, 0.25, 0.35, 0.45])

# sigma1 and sigma2 are covariance matrices (2D square arrays)
# Create positive semi-definite covariance matrices
dim = 4
A1 = np.random.randn(dim, dim)
sigma1 = A1 @ A1.T  # Ensure positive semi-definite
A2 = np.random.randn(dim, dim)
sigma2 = A2 @ A2.T  # Ensure positive semi-definite

# eps is a small regularization constant
eps = 1e-06

ARGS = {
    "mu1": mu1,
    "sigma1": sigma1,
    "mu2": mu2,
    "sigma2": sigma2,
    "eps": eps,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
poincare_loss Ran
ran; our contract draft was wrong, not the code
LukasStruppek/Plug-and-Play-Attacks/attacks/optimize.py
code served (permissive licence) · get_code("9eeaa864194d2b12")
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 1, dtype family float, shape (2,) 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)

# Create outputs tensor: batch_size=2, embedding_dim=4
outputs = torch.randn(2, 4, dtype=torch.float32)

# Create targets tensor: batch_size=2, with class indices in range [0, 4)
targets = torch.tensor([0, 2], dtype=torch.long)

# xi parameter
xi = 0.0001

ARGS = {
    "outputs": outputs,
    "targets": targets,
    "xi": xi,
}
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 1, dtype family float, shape (2,) — shape (2,) 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
power_iteration Ran
ran; our contract draft was wrong, not the code
ajbrock/BigGAN-PyTorch/layers.py
code served (permissive licence) · get_code("28d3a35157f2916d")
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 torch
import torch.nn.functional as F

torch.manual_seed(0)

# Construct valid arguments for power_iteration
# W: weight matrix that will be multiplied with u and v vectors
# Shape should allow matmul operations: (4, 3) so u (1, 4) @ W (4, 3) = (1, 3)
W = torch.randn(4, 3)

# u_: list of initial vectors
# Each should be a 1D tensor with size matching W's first dimension
u_ = [
    torch.randn(1, 4),
    torch.randn(1, 4),
]

# update: boolean flag
update = True

# eps: small epsilon for numerical stability
eps = 1e-12

ARGS = {
    "W": W,
    "u_": u_,
    "update": update,
    "eps": eps,
}
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 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
sqrt_newton_schulz Ran
ran; our contract draft was wrong, not the code
ajbrock/BigGAN-PyTorch/inception_utils.py
code served (permissive licence) · get_code("c39eebccbb5e86a6")
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 3, dtype family float, shape (2, 4, 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)

# Create a small batch of square matrices (batch_size=2, dim=4)
# The function expects A to be shape (batchSize, dim, dim)
batch_size = 2
dim = 4

# Create random positive semi-definite matrices by A = M @ M.T
M = torch.randn(batch_size, dim, dim, dtype=torch.float32)
A = torch.bmm(M, M.transpose(1, 2))

# numIters is the number of Newton-Schulz iterations
numIters = 3

# dtype is optional, can be None or a torch dtype string
dtype = None

ARGS = {
    "A": A,
    "numIters": numIters,
    "dtype": dtype,
}
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 3, dtype family float, shape (2, 4, 4) — shape (2, 4, 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
torch_cov Ran
ran; our contract draft was wrong, not the code
ajbrock/BigGAN-PyTorch/inception_utils.py
code served (permissive licence) · get_code("4a2b2f288be2a186")
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 2, dtype family float, shape (5, 5) 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)

# Create a 2-D tensor with shape (3, 5)
# 3 variables, 5 observations
m = torch.randn(3, 5)

ARGS = {
    "m": m,
    "rowvar": 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 2, dtype family float, shape (5, 5) — shape (5, 5) 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
truncated_z_sample Ran
ran, honoured the contract we drafted
ajbrock/BigGAN-PyTorch/TFHub/biggan_v1.py
code served (permissive licence) · get_code("b72f0c209b7b64be")
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 (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 numpy as np
from scipy.stats import truncnorm

ARGS = {
    "batch_size": 2,
    "z_dim": 4,
    "truncation": 0.5,
    "seed": 42,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — 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 (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
write_precision_list Ran
ran; our contract draft was wrong, not the code
lukasstruppek/plug-and-play-attacks/attack.py
code served (permissive licence) · get_code("410e110382621c40")
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 str. 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 csv
import tempfile
import os

# Create a temporary directory for the output file
temp_dir = tempfile.gettempdir()
filename = os.path.join(temp_dir, "test_precision")

# Create a sample precision_list with multiple rows
# Each row represents precision values for different classes or iterations
precision_list = [
    [0.95, 0.87, 0.92],
    [0.91, 0.89, 0.94],
    [0.93, 0.85, 0.90],
    [0.96, 0.88, 0.91]
]

ARGS = {
    "filename": filename,
    "precision_list": precision_list
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
InversionNet Not yet run
unverified (harvested, no recorded run)
AI-secure/GMI-Attack/Celeba/generator.py
pointer only (licence: NONE) · get_code("3b56f1895629495e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AI-secure/GMI-Attack 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. No invocation recorded.

Optimization Not yet run
unverified (harvested, no recorded run)
LukasStruppek/Plug-and-Play-Attacks/attacks/optimize.py
code served (permissive licence) · get_code("c29018fcd5fb7cfa")
How it ran

no invocation recorded.

dist_inversion Not yet run
unverified (harvested, no recorded run)
SCccc21/Knowledge-Enriched-DMI/attack.py
code served (permissive licence) · get_code("ef6717b52bd16215")
How it ran

no invocation recorded.

log_sum_exp Not yet run
unverified (harvested, no recorded run)
SCccc21/Knowledge-Enriched-DMI/attack.py
code served (permissive licence) · get_code("265774c3878176e5")
How it ran

no invocation recorded.

low2high Not yet run
unverified (harvested, no recorded run)
SCccc21/Knowledge-Enriched-DMI/attack.py
code served (permissive licence) · get_code("dece9a6e3aff80cf")
How it ran

no invocation recorded.

proj Not yet run
unverified (harvested, no recorded run)
ajbrock/BigGAN-PyTorch/layers.py
pointer only (licence: MIT); the stored copy get_code serves, from mshahbazi72/cGANTransfer, is pointer only (licence: NONE) · get_code("4015ab1f3ab9b881")
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 mshahbazi72/cGANTransfer, 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. No invocation recorded.

reparameterize Not yet run
unverified (harvested, no recorded run)
SCccc21/Knowledge-Enriched-DMI/attack.py
code served (permissive licence) · get_code("3c7bb63b7354af4f")
How it ran

no invocation recorded.

run Not yet run
unverified (harvested, no recorded run)
ajbrock/BigGAN-PyTorch/inception_tf13.py
code served (permissive licence) · get_code("ac122c2c1495ce94")
How it ran

no invocation recorded.

save_tensor_images Not yet run
unverified (harvested, no recorded run)
SCccc21/Knowledge-Enriched-DMI/attack.py
code served (permissive licence) · get_code("ddce921e8795376f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 36 samples lifted from this paper's linked repositories, 36 carry a function identity and 0 do not. Of the 36 distinct functions with an identity, 25 are also present in other papers whose code we hold (22 with at least one paper dated earlier, 4 the same month, 20 later) and 11 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
find_classes 30 other papers
16 dated earlier, 12 later, 2 same year, order not determinable
1406.2661 (2014-06)
Generative Adversarial Networks
1612.06321 (2016-12)
Large-Scale Image Retrieval with Attentive Deep Local Features
1809.04729 (2018-09)
A Less Biased Evaluation of Out-of-distribution Sample Detectors
and 27 more not named here
gram_schmidt 28 other papers
14 dated earlier, 12 later, 2 same year, order not determinable · 5 only as an assembly brick
1809.11096 (2018-09)
Large Scale GAN Training for High Fidelity Natural Image Synthesis
1811.10597 (2018-11)
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
1910.05852 (2019-10)
Implicit competitive regularization in GANs
and 25 more not named here
proj 28 other papers
14 dated earlier, 12 later, 2 same year, order not determinable · 5 only as an assembly brick
1809.11096 (2018-09)
Large Scale GAN Training for High Fidelity Natural Image Synthesis
1811.10597 (2018-11)
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
1910.05852 (2019-10)
Implicit competitive regularization in GANs
and 25 more not named here
power_iteration 25 other papers
12 dated earlier, 11 later, 2 same year, order not determinable · 5 only as an assembly brick
1809.11096 (2018-09)
Large Scale GAN Training for High Fidelity Natural Image Synthesis
1811.10597 (2018-11)
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
1910.05852 (2019-10)
Implicit competitive regularization in GANs
and 22 more not named here
is_image_file 22 other papers
12 dated earlier, 8 later, 2 same year, order not determinable
1406.2661 (2014-06)
Generative Adversarial Networks
1603.08511 (2016-03)
Colorful Image Colorization
1805.08318 (2018-05)
Self-Attention Generative Adversarial Networks
and 19 more not named here
G_arch 18 other papers
9 dated earlier, 1 the same month, 7 later, 1 same year, order not determinable · 3 only as an assembly brick
1809.11096 (2018-09)
Large Scale GAN Training for High Fidelity Natural Image Synthesis
1811.10597 (2018-11)
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
1912.05270 (2019-12)
MineGAN: effective knowledge transfer from GANs to target domains with few images
and 15 more not named here
D_arch 15 other papers
7 dated earlier, 1 the same month, 6 later, 1 same year, order not determinable
1809.11096 (2018-09)
Large Scale GAN Training for High Fidelity Natural Image Synthesis
1811.10597 (2018-11)
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
1912.05270 (2019-12)
MineGAN: effective knowledge transfer from GANs to target domains with few images
and 12 more not named here
torch_cov 12 other papers
4 dated earlier, 6 later, 2 same year, order not determinable
1406.2661 (2014-06)
Generative Adversarial Networks
1811.10597 (2018-11)
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
1912.05270 (2019-12)
MineGAN: effective knowledge transfer from GANs to target domains with few images
and 9 more not named here
loss_hinge_dis 11 other papers
5 dated earlier, 4 later, 2 same year, order not determinable
1809.11096 (2018-09)
Large Scale GAN Training for High Fidelity Natural Image Synthesis
1912.00953 (2019-12)
LOGAN: Latent Optimisation for Generative Adversarial Networks
1912.05270 (2019-12)
MineGAN: effective knowledge transfer from GANs to target domains with few images
and 8 more not named here
loss_dcgan_dis 10 other papers
4 dated earlier, 4 later, 2 same year, order not determinable
1809.11096 (2018-09)
Large Scale GAN Training for High Fidelity Natural Image Synthesis
1912.05270 (2019-12)
MineGAN: effective knowledge transfer from GANs to target domains with few images
2008.10599 (2020-08)
The Hessian Penalty: A Weak Prior for Unsupervised Disentanglement
and 7 more not named here
make_dataset 10 other papers
5 dated earlier, 3 later, 2 same year, order not determinable
1406.2661 (2014-06)
Generative Adversarial Networks
1809.11096 (2018-09)
Large Scale GAN Training for High Fidelity Natural Image Synthesis
1912.05270 (2019-12)
MineGAN: effective knowledge transfer from GANs to target domains with few images
and 7 more not named here
G_arch 9 other papers
3 dated earlier, 1 the same month, 4 later, 1 same year, order not determinable
1912.05270 (2019-12)
MineGAN: effective knowledge transfer from GANs to target domains with few images
2008.10599 (2020-08)
The Hessian Penalty: A Weak Prior for Unsupervised Disentanglement
2108.07668 (2021-08)
Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation
and 6 more not named here
loss_dcgan_gen 9 other papers
3 dated earlier, 4 later, 2 same year, order not determinable
1809.11096 (2018-09)
Large Scale GAN Training for High Fidelity Natural Image Synthesis
2008.10599 (2020-08)
The Hessian Penalty: A Weak Prior for Unsupervised Disentanglement
2108.07668 (2021-08)
Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation
and 6 more not named here
D_arch 8 other papers
3 dated earlier, 1 the same month, 3 later, 1 same year, order not determinable
1912.05270 (2019-12)
MineGAN: effective knowledge transfer from GANs to target domains with few images
2008.10599 (2020-08)
The Hessian Penalty: A Weak Prior for Unsupervised Disentanglement
2108.07668 (2021-08)
Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation
and 5 more not named here
sqrt_newton_schulz 6 other papers
4 dated earlier, 2 same year, order not determinable
1406.2661 (2014-06)
Generative Adversarial Networks
1811.10597 (2018-11)
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
1912.05270 (2019-12)
MineGAN: effective knowledge transfer from GANs to target domains with few images
and 3 more not named here
denorm 5 other papers
3 dated earlier, 2 later
1805.08318 (2018-05)
Self-Attention Generative Adversarial Networks
1809.11096 (2018-09)
Large Scale GAN Training for High Fidelity Natural Image Synthesis
2010.02637 (2020-10)
Weakly Supervised Disentangled Generative Causal Representation Learning
and 2 more not named here
numpy_calculate_frechet_distance 5 other papers
3 dated earlier, 2 same year, order not determinable
1406.2661 (2014-06)
Generative Adversarial Networks
1912.05270 (2019-12)
MineGAN: effective knowledge transfer from GANs to target domains with few images
2004.00917 (2020-04)
Controllable Orthogonalization in Training DNNs
and 2 more not named here
dconv_bn_relu
brick of this paper's assembly: helper
4 other papers
1 dated earlier, 3 later
2010.04092 (2020-10)
Knowledge-Enriched Distributional Model Inversion Attacks
2207.12263 (2022-07)
SecretGen: Privacy Recovery on Pre-trained Models via Distribution Discrimination
2402.04013 (2024-02)
Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses
and 1 more not named here
run 4 other papers
1 dated earlier, 1 later, 2 same year, order not determinable
1912.05270 (2019-12)
MineGAN: effective knowledge transfer from GANs to target domains with few images
aaai_20247 (2022 (year only))
An Adversarial Framework for Generating Unseen Images by Activation Maximization
aaai_20902 (2022 (year only))
CLPA: Clean-Label Poisoning Availability Attacks Using Generative Adversarial Nets
and 1 more not named here
l2normalize 2 other papers
2 dated earlier
1802.05957 (2018-02)
Spectral Normalization for Generative Adversarial Networks
1809.11096 (2018-09)
Large Scale GAN Training for High Fidelity Natural Image Synthesis

Shown: the 20 functions present in the most other papers. 5 more shared functions are not listed 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

Model inversion attacks (MIAs) aim to create synthetic images that reflect the class-wise characteristics from a target classifier's private training data by exploiting the model's learned knowledge. Previous research has developed generative MIAs that use generative adversarial networks (GANs) as image priors tailored to a specific target model. This makes the attacks time-and resource-consuming, inflexible, and susceptible to distributional shifts between datasets. To overcome these drawbacks, we present Plug & Play Attacks, which relax the dependency between the target model and image prior, and enable the use of a single GAN to attack a wide range of targets, requiring only minor adjustments to the attack. Moreover, we show that powerful MIAs are possible even with publicly available pre-trained GANs and under strong distributional shifts, for which previous approaches fail to produce meaningful results. Our extensive evaluation confirms the improved robustness and flexibility of Plug & Play Attacks and their ability to create high-quality images revealing sensitive class characteristics.

For agents

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

get_harvested_code_for_paper("2201.12179")
get_code_for_paper("2201.12179")
have("2201.12179")

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

curl https://syntology.ai/api/ran/2201.12179.json

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

[![Syntology run record](https://syntology.ai/api/ran/2201.12179.svg)](https://syntology.ai/paper/2201.12179)

Connect an agent — have() is free.