SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.08500 · 2023

The Devil's Advocate: Shattering the Illusion of Unexploitable Data using Diffusion Models

arXiv · PDF · Open in the Atlas

Code that ran

16 of 17 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; 2 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 13 failures of our instrument; 1 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/2303.08500.json · badge: /api/ran/2303.08500.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
hmdolatabadi/avatar canonical (classifier label)
classifier basis not recorded on the link
16 ran · 1 no recorded run
FunctionStatusWhere it lives
DenseNet121 Ran
ran; our contract draft was wrong, not the code
hmdolatabadi/avatar/models/DenseNet.py
code served (permissive licence) · get_code("a3cedf1d509b37f2")
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 DenseNet. 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

torch.manual_seed(0)

ARGS = {
    'num_classes': 10
}
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 DenseNet — a DenseNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DenseNet 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
DenseNet169 Ran
ran; our contract draft was wrong, not the code
hmdolatabadi/avatar/models/DenseNet.py
code served (permissive licence) · get_code("db62cd85a5a44695")
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 DenseNet. 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
import math

torch.manual_seed(0)

# DenseNet169 takes num_classes as a parameter
ARGS = {
    'num_classes': 10
}
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 DenseNet — a DenseNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DenseNet 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
DenseNet201 Ran
ran; our contract draft was wrong, not the code
hmdolatabadi/avatar/models/DenseNet.py
code served (permissive licence) · get_code("3ef0755182d96334")
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 DenseNet. 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
import math

torch.manual_seed(0)

ARGS = {
    "num_classes": 10
}
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 DenseNet — a DenseNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DenseNet 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
Normalize Ran
ran; our contract draft was wrong, not the code
hmdolatabadi/avatar/ddpm/unet_ddpm.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.

ResNet18 Ran
ran; our contract draft was wrong, not the code
hmdolatabadi/avatar/models/ResNet.py
code served (permissive licence) · get_code("336a886b8ba6ecb3")
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 ResNet. 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

torch.manual_seed(0)

ARGS = {
    'num_classes': 10
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
ResNet34 Ran
ran; our contract draft was wrong, not the code
hmdolatabadi/avatar/models/ResNet.py
code served (permissive licence) · get_code("d8df895be3c7b30e")
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 ResNet. 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

torch.manual_seed(0)

ARGS = {
    'num_classes': 10
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
ResNet50 Ran
ran; our contract draft was wrong, not the code
hmdolatabadi/avatar/models/ResNet.py
code served (permissive licence) · get_code("4a3e54f8626a4284")
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 ResNet. 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

torch.manual_seed(0)

ARGS = {
    "num_classes": 10
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
approx_standard_normal_cdf Ran
ran; our contract draft was wrong, not the code
hmdolatabadi/avatar/guided_diffusion/losses.py
pointer only (licence: MIT); the stored copy get_code serves, from quandao10/slct, is pointer only (licence: NONE) · get_code("cfd76fd0d89574a4")
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 quandao10/slct, 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.

cross_entropy Ran
ran on a synthesized input
hmdolatabadi/avatar/ISS_augs.py
code served (permissive licence) · get_code("4cabce0764d52cf1")
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

torch.manual_seed(0)

# Create input tensor: batch_size=2, num_classes=4
# Shape: (2, 4) - 2 samples, 4 classes
input_tensor = torch.FloatTensor([[1.1, 2.8, 1.3, 0.5], 
                                  [1.1, 2.1, 4.8, 0.2]])
input_tensor.requires_grad_(True)

# Create target tensor (soft targets): batch_size=2, num_classes=4
# Shape: (2, 4) - soft probability distributions
target_tensor = torch.FloatTensor([[0.05, 0.9, 0.03, 0.02],
                                   [0.05, 0.05, 0.85, 0.05]])

ARGS = {
    'input': input_tensor,
    'target': target_tensor,
    'size_average': True
}
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
discretized_gaussian_log_likelihood Ran
ran; our contract draft was wrong, not the code
hmdolatabadi/avatar/guided_diffusion/losses.py
pointer only (licence: MIT); the stored copy get_code serves, from quandao10/slct, is pointer only (licence: NONE) · get_code("cd33283d615fb3d7")
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 quandao10/slct, 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.

dumps_data Ran
ran; our contract draft was wrong, not the code
hmdolatabadi/avatar/AVATAR_sanitization.py
code served (permissive licence) · get_code("cadb98df0b43c793")
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 bytes. 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 pickle
import torch
import numpy as np

# Set seed for reproducibility
torch.manual_seed(0)

# Create various serializable objects to test dumps_data
obj_dict = {
    "key1": "value1",
    "key2": 42,
    "key3": [1, 2, 3]
}

obj_list = [1, 2, 3, "test", {"nested": "dict"}]

obj_tensor = torch.randn(2, 4)

obj_numpy = np.array([[1, 2, 3], [4, 5, 6]])

class SimpleClass:
    def __init__(self):
        self.data = "test_data"
        self.value = 123

obj_custom = SimpleClass()

obj_tuple = (1, 2, "three", [4, 5])

obj_string = "This is a simple string"

obj_number = 42.5

# Test with dict - this is a common serialization target
ARGS = {
    "obj": obj_dict
}
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 bytes — a bytes output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a bytes 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
get_timestep_embedding Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hmdolatabadi/avatar/ddpm/unet_ddpm.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
loads_data Ran
ran; our contract draft was wrong, not the code
hmdolatabadi/avatar/AVATAR_evaluation.py
pointer only (licence: MIT); the stored copy get_code serves, from s-enmt/MMFT, is pointer only (licence: NOASSERTION) · get_code("2bc7277fbb33cc3f")
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 s-enmt/MMFT, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

nonlinearity Ran
ran; our contract draft was wrong, not the code
hmdolatabadi/avatar/ddpm/unet_ddpm.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
normal_kl Ran
ran, honoured the contract we drafted
hmdolatabadi/avatar/guided_diffusion/losses.py
pointer only (licence: MIT); the stored copy get_code serves, from facebookresearch/agrol, is pointer only (licence: NOASSERTION) · get_code("cf2798b666b231ca")
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 facebookresearch/agrol, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

onehot Ran
ran, honoured the contract we drafted
hmdolatabadi/avatar/ISS_augs.py
code served (permissive licence) · get_code("a2847ea5f23c1e07")
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 (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)

ARGS = {
    "size": 5,
    "target": 2
}
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 (5,) — shape (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
rand_bbox Not yet run
unverified (harvested, no recorded run)
hmdolatabadi/avatar/ISS_augs.py
code served (permissive licence) · get_code("b3d09a4dd10e16e3")
How it ran

no invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 16 are also present in other papers whose code we hold (14 with at least one paper dated earlier, 6 the same month, 15 later) and 1 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
normal_kl 160 other papers
27 dated earlier, 5 the same month, 126 later, 2 same year, order not determinable · 19 only as an assembly brick
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
and 157 more not named here
nonlinearity 156 other papers
25 dated earlier, 5 the same month, 125 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
approx_standard_normal_cdf 154 other papers
27 dated earlier, 5 the same month, 120 later, 2 same year, order not determinable · 17 only as an assembly brick
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
and 151 more not named here
discretized_gaussian_log_likelihood 128 other papers
27 dated earlier, 5 the same month, 94 later, 2 same year, order not determinable · 16 only as an assembly brick
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
and 125 more not named here
get_timestep_embedding 91 other papers
20 dated earlier, 5 the same month, 65 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
19 dated earlier, 4 the same month, 67 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
ResNet18 27 other papers
10 dated earlier, 17 later
1605.07146 (2016-05)
Wide Residual Networks
1901.09847 (2019-01)
Error Feedback Fixes SignSGD and other Gradient Compression Schemes
1910.09652 (2019-10)
Kernelized Wasserstein Natural Gradient
and 24 more not named here
ResNet34 24 other papers
13 dated earlier, 10 later, 1 same year, order not determinable
1605.07146 (2016-05)
Wide Residual Networks
1811.12814 (2018-11)
Graph-Based Global Reasoning Networks
2002.12047 (2020-02)
FMix: Enhancing Mixed Sample Data Augmentation
and 21 more not named here
ResNet50 14 other papers
5 dated earlier, 9 later
1605.07146 (2016-05)
Wide Residual Networks
1811.12814 (2018-11)
Graph-Based Global Reasoning Networks
2006.13554 (2020-06)
Normalized Loss Functions for Deep Learning with Noisy Labels
and 11 more not named here
DenseNet121 11 other papers
6 dated earlier, 5 later
2006.15815 (2020-06)
Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum
2105.13937 (2021-05)
Polygonal Unadjusted Langevin Algorithms: Creating stable and efficient adaptive algorithms for neural networks
2108.09976 (2021-08)
Revealing the Distributional Vulnerability of Discriminators by Implicit Generators
and 8 more not named here
DenseNet169 9 other papers
5 dated earlier, 4 later
2006.15815 (2020-06)
Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum
2108.09976 (2021-08)
Revealing the Distributional Vulnerability of Discriminators by Implicit Generators
2201.13329 (2022-01)
Can Adversarial Training Be Manipulated By Non-Robust Features?
and 6 more not named here
DenseNet201 9 other papers
5 dated earlier, 4 later
2006.15815 (2020-06)
Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum
2108.09976 (2021-08)
Revealing the Distributional Vulnerability of Discriminators by Implicit Generators
2201.13329 (2022-01)
Can Adversarial Training Be Manipulated By Non-Robust Features?
and 6 more not named here
loads_data 5 other papers
5 later
aaai_28365 (2024 (year only))
AGS: Affordable and Generalizable Substitute Training for Transferable Adversarial Attack
2401.06187 (2024-01)
Scissorhands: Scrub Data Influence via Connection Sensitivity in Networks
2402.11846 (2024-02)
UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models
and 2 more not named here
dumps_data 3 other papers
3 later
aaai_28365 (2024 (year only))
AGS: Affordable and Generalizable Substitute Training for Transferable Adversarial Attack
2401.06187 (2024-01)
Scissorhands: Scrub Data Influence via Connection Sensitivity in Networks
2402.11846 (2024-02)
UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models
onehot 2 other papers
1 dated earlier, 1 later
1905.04899 (2019-05)
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
2403.19600 (2024-03)
Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model
rand_bbox 1 other paper
1 dated earlier
1905.04899 (2019-05)
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features

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

Protecting personal data against exploitation of machine learning models is crucial. Recently, availability attacks have shown great promise to provide an extra layer of protection against the unauthorized use of data to train neural networks. These methods aim to add imperceptible noise to clean data so that the neural networks cannot extract meaningful patterns from the protected data, claiming that they can make personal data "unexploitable." This paper provides a strong countermeasure against such approaches, showing that unexploitable data might only be an illusion. In particular, we leverage the power of diffusion models and show that a carefully designed denoising process can counteract the effectiveness of the data-protecting perturbations. We rigorously analyze our algorithm, and theoretically prove that the amount of required denoising is directly related to the magnitude of the data-protecting perturbations. Our approach, called AVATAR, delivers state-of-the-art performance against a suite of recent availability attacks in various scenarios, outperforming adversarial training even under distribution mismatch between the diffusion model and the protected data. Our findings call for more research into making personal data unexploitable, showing that this goal is far from over. Our implementation is available at this repository: https://github.com/hmdolatabadi/AVATAR.

For agents

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

get_harvested_code_for_paper("2303.08500")
get_code_for_paper("2303.08500")
have("2303.08500")

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

curl https://syntology.ai/api/ran/2303.08500.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.08500.svg)](https://syntology.ai/paper/2303.08500)

Connect an agent — have() is free.