SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.00542 · ICLR · 2023

Watch Out! Simple Horizontal Class Backdoor Can Trivially Evade Defense

Zhi Zhang, Hua Ma, Shang Wang, Sydney Australia, Yansong Gao, Anmin Fu, Derek Abbott, Huming Qiu, Minhui Xue, Alsharif Abuadbba, Surya Nepal, Derek Watch

arXiv · PDF · Open in the Atlas

Code that ran

16 of 22 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 1 has no contract verdict; 14 failures of our instrument; 6 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/2310.00542.json · badge: /api/ran/2310.00542.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
TDteach/Demon-in-the-Variant canonical (classifier label)
classifier basis: census
7 ran · 3 no recorded run
naiyeleo/ABS canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
shihe98/HCB canonical (classifier label)
classifier basis: census
2 ran · 0 no recorded run
shihe98/hcb canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
AdelaideAuto-IDLab/Februus community
Papers with Code archive
1 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
Gwinhen/MOTH community
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
Hbeta Ran
ran, honoured the contract we drafted
TDteach/Demon-in-the-Variant/tsne.py
code served (permissive licence) · get_code("77fb404ad78a22d9")
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 numpy as np

# Create a small distance matrix as the D parameter
# This should be a 1D array of distances
D = np.array([0.0, 0.5, 1.0, 1.5, 2.0])

# Create the beta parameter
beta = 1.0

# Construct the ARGS dictionary with all parameters
ARGS = {
    'D': D,
    'beta': beta
}
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 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
build_base_model Ran
ran; our contract draft was wrong, not the code
TDteach/Demon-in-the-Variant/pysrc/train_cifar10.py
code served (permissive licence) · get_code("874d05e9545938a1")
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 Functional. 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 tensorflow as tf

ARGS = {
    'x': None,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
six, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Functional — a Functional output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Functional 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
build_base_model Ran
ran; our contract draft was wrong, not the code
TDteach/Demon-in-the-Variant/pysrc/train_gtsrb.py
code served (permissive licence) · get_code("e15bd05849cc4332")
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 Functional. 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 tensorflow as tf

ARGS = {
    'x': None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
six, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Functional — a Functional output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Functional 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
build_model Ran
ran; our contract draft was wrong, not the code
TDteach/Demon-in-the-Variant/pysrc/train_gtsrb.py
code served (permissive licence) · get_code("45579f864dad8357")
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 Functional. 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 tensorflow as tf

# Set seed for reproducibility
tf.random.set_seed(0)

# Define ARGS dict with all parameters for build_model
ARGS = {
    'mode': 'normal'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
six, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Functional — a Functional output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Functional 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
channel_shuffle Ran
ran; our contract draft was wrong, not the code
naiyeleo/ABS/TrojAI_competition/round2/abs_pytorch1_color_simple_filter4_8_6_3_determinism.py
pointer only (licence: NONE); the stored copy get_code serves, from ddghost/new_darts, is pointer only (licence: NONE) · get_code("b9da06d4f527dd6c")
How it ran

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

deprocess Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
naiyeleo/ABS/TrojAI_competition/round1/abs_pytorch_round1.py
pointer only (licence: NONE); the stored copy get_code serves, from wanlunsec/beatrix, is pointer only (licence: NONE) · get_code("f7334fdb122d1c51")
How it ran

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

getTrans Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
shihe98/HCB/GTSRB/Model/utils_model_outsourcing.py
code served (permissive licence) · get_code("2267cf1bf4bcc344")
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 (32, 32, 3) 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

# The function expects 'data' to be a 3D array-like object
# that can be indexed with [k][i][j] where:
# - k ranges over 3 (color channels)
# - i ranges over 32 (height)
# - j ranges over 32 (width)
# 
# The function transposes from (channels, height, width) to (height, width, channels)

data = np.zeros((3, 32, 32))
for k in range(3):
    for i in range(32):
        for j in range(32):
            data[k][i][j] = k * 1000 + i * 10 + j

ARGS = {
    "data": data
}
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 (32, 32, 3) — shape (32, 32, 3) 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_backdoor_train Ran
ran on a synthesized input
shihe98/hcb/GTSRB/Model/utils_model_outsourcing.py
code served (permissive licence) · get_code("92f6ebd6ff7231bf")
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 DataLoader. 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 copy
import torch
import numpy as np
import torch.utils.data as Data

torch.manual_seed(0)

# The function get_backdoor_train() takes no parameters
# It loads data from files, but we need to mock that behavior
# Since we can't do file I/O, we'll create the necessary data structures

# Create mock data arrays with the expected shapes
# train_data, train_label, rain_imgs, rain_labs should be numpy arrays
# The function expects 3D data (channels=3, height=32, width=32)

train_data = np.random.rand(10, 3, 32, 32).astype(np.float32)
train_label = np.random.randint(0, 10, 10).astype(np.float32)
rain_imgs = np.random.rand(5, 3, 32, 32).astype(np.float32)
rain_labs = np.random.randint(0, 10, 5).astype(np.float32)

# Monkey-patch np.load to return our mock data
original_load = np.load
load_map = {
    './data/data.npy': train_data,
    './data/label.npy': train_label,
    './data/rain.npy': rain_imgs,
    './data/rainLab.npy': rain_labs,
}

def mock_load(path, *args, **kwargs):
    if path in load_map:
        return load_map[path].copy()
    return original_load(path, *args, **kwargs)

np.load = mock_load

# Now the function can be called with no arguments
ARGS = {}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataLoader — a DataLoader output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataLoader 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_triggerData Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
shihe98/hcb/GTSRB/Model/utils_model_outsourcing.py
code served (permissive licence) · get_code("8d23eca23f539e84")
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 (3, 32, 32) 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 numpy as np
import copy

# Analyze the function:
# - data: needs to support indexing [i][j][k] and deepcopy
# - a: a scalar value to assign
# - The function accesses indices: i in range(3), j in range(32), k in range(32)
# - So data needs shape (3, 32, 32) minimum

# Create a 3D tensor/array with shape (3, 32, 32)
torch.manual_seed(0)
data = torch.randn(3, 32, 32)

# Create a scalar value for parameter a
a = 42.0

ARGS = {
    "data": data,
    "a": a
}
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 Tensor, ndim 3, dtype family float, shape (3, 32, 32) — shape (3, 32, 32) 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
no Ran
ran; our contract draft was wrong, not the code
AdelaideAuto-IDLab/Februus/face/Februus.py
pointer only (licence: NONE) · get_code("7d8578b316548dd5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AdelaideAuto-IDLab/Februus 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.

options_to_json Ran
ran; our contract draft was wrong, not the code
TDteach/Demon-in-the-Variant/pysrc/utils.py
code served (permissive licence) · get_code("5117993745c7bae0")
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 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 json

class Options:
    def __init__(self):
        self.learning_rate = 0.001
        self.batch_size = 32
        self.epochs = 10
        self.model_name = "test_model"
        self.seed = 42
        self.verbose = True

options = Options()

ARGS = {
    'options': options
}
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 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
pca Ran
ran; our contract draft was wrong, not the code
TDteach/Demon-in-the-Variant/tsne.py
code served (permissive licence) · get_code("f60cb3cead55f81b")
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 (5, 3) 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(0)

# Create a small test dataset: 5 samples, 10 features
X = np.random.randn(5, 10).astype(np.float32)

# Set no_dims to reduce to 3 dimensions
no_dims = 3

ARGS = {
    'X': X,
    'no_dims': no_dims
}
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 2, dtype family float, shape (5, 3) — shape (5, 3) 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
preprocess Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
naiyeleo/ABS/TrojAI_competition/round1/abs_pytorch_round1.py
pointer only (licence: NONE); the stored copy get_code serves, from wanlunsec/beatrix, is pointer only (licence: NONE) · get_code("06fcb055d047c43d")
How it ran

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

test_accuracy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
shihe98/HCB/GTSRB/Model/utils_model_outsourcing.py
code served (permissive licence) · get_code("39f23426bccb25cd")
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 float, ndim 0, dtype family float, shape () 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

torch.manual_seed(0)

# Define a minimal model that satisfies the function's usage
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc = nn.Linear(4, 3)  # 4 input features, 3 output classes
    
    def forward(self, x):
        return self.fc(x)

# Create model instance
model = SimpleModel()

# Create a minimal testloader as a list of (images, labels) tuples
# Batch size 2, image features 4, 3 classes
testloader = [
    (torch.randn(2, 4), torch.tensor([0, 1])),
    (torch.randn(2, 4), torch.tensor([2, 0])),
]

ARGS = {
    "model": model,
    "testloader": testloader,
}
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 float, 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
unno Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from AdelaideAuto-IDLab/Februus
pointer only; the stored copy get_code serves, from AdelaideAuto-IDLab/Februus, is pointer only (licence: NONE) · get_code("1ed9bb9126b74824")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

x2p Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
TDteach/Demon-in-the-Variant/tsne.py
code served (permissive licence) · get_code("654e67f1bec03fc8")
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 (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 numpy as np

# The function x2p expects:
# - X: a 2D numpy array of shape (n, d) containing n data points in d dimensions
# - tol: a float tolerance value
# - perplexity: a float perplexity value

# Create a small dataset: 5 points in 3 dimensions
np.random.seed(0)
X = np.random.randn(5, 3).astype(np.float64)

ARGS = {
    'X': X,
    'tol': 1e-5,
    'perplexity': 30.0
}
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 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
Trigger Not yet run
unverified (harvested, no recorded run)
Gwinhen/MOTH/src/inversion.py
code served (permissive licence) · get_code("098112848b087db6")
How it ran

no invocation recorded.

getlayer_output Not yet run
unverified (harvested, no recorded run)
naiyeleo/ABS/abs.py
pointer only (licence: NONE) · get_code("dd61aa4cb050a0de")
How it ran

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

parse_record Not yet run
unverified (harvested, no recorded run)
TDteach/Demon-in-the-Variant/pysrc/train_cifar10.py
code served (permissive licence) · get_code("4e8aeb9bb95b5b61")
How it ran

no invocation recorded.

poison_one Not yet run
unverified (harvested, no recorded run)
AdelaideAuto-IDLab/Februus/face/Februus.py
pointer only (licence: NONE) · get_code("50d5614af6b6f7c5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AdelaideAuto-IDLab/Februus 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.

split_model Not yet run
unverified (harvested, no recorded run)
TDteach/Demon-in-the-Variant/pysrc/train_cifar10.py
code served (permissive licence) · get_code("a756332b6091f3b8")
How it ran

no invocation recorded.

split_model Not yet run
unverified (harvested, no recorded run)
TDteach/Demon-in-the-Variant/pysrc/train_gtsrb.py
code served (permissive licence) · get_code("69b6b3cbe737eaf2")
How it ran

no invocation recorded.

Also present in other papers' code

Of 22 samples lifted from this paper's linked repositories, 22 carry a function identity and 0 do not. Of the 21 distinct functions with an identity, 14 are also present in other papers whose code we hold (14 with at least one paper dated earlier, 0 the same month, 2 later) and 7 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
channel_shuffle 19 other papers
17 dated earlier, 2 later · 2 only as an assembly brick
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1606.02147 (2016-06)
ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
1805.12549 (2018-05)
Channel Gating Neural Networks
and 16 more not named here
Hbeta 3 other papers
2 dated earlier, 1 later
1606.02185 (2016-06)
Towards a Neural Statistician
1908.00686 (2019-08)
Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection
2510.07746 (2025-10)
t-SNE Exaggerates Clusters, Provably
pca 2 other papers
2 dated earlier
1606.02185 (2016-06)
Towards a Neural Statistician
1908.00686 (2019-08)
Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection
x2p 2 other papers
2 dated earlier
1606.02185 (2016-06)
Towards a Neural Statistician
1908.00686 (2019-08)
Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection
build_base_model 1 other paper
1 dated earlier
1908.00686 (2019-08)
Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection
build_base_model 1 other paper
1 dated earlier
1908.00686 (2019-08)
Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection
build_model 1 other paper
1 dated earlier
1908.00686 (2019-08)
Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection
deprocess 1 other paper
1 dated earlier
2209.11715 (2022-09)
The "Beatrix'' Resurrections: Robust Backdoor Detection via Gram Matrices
options_to_json 1 other paper
1 dated earlier
1908.00686 (2019-08)
Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection
parse_record 1 other paper
1 dated earlier
1908.00686 (2019-08)
Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection
poison_one
brick of this paper's assembly: entry
1 other paper
1 dated earlier
1908.03369 (2019-08)
Februus: Input Purification Defense Against Trojan Attacks on Deep Neural Network Systems
preprocess 1 other paper
1 dated earlier
2209.11715 (2022-09)
The "Beatrix'' Resurrections: Robust Backdoor Detection via Gram Matrices
split_model 1 other paper
1 dated earlier
1908.00686 (2019-08)
Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection
unno
brick of this paper's assembly: helper
1 other paper
1 dated earlier
1908.03369 (2019-08)
Februus: Input Purification Defense Against Trojan Attacks on Deep Neural Network Systems

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

All current backdoor attacks on deep learning (DL) models fall under the category of a vertical class backdoor (VCB)-class-dependent. In VCB attacks, any sample from a class activates the implanted backdoor when the secret trigger is present, regardless of whether it is a sub-type source-class-agnostic backdoor or a source-classspecific backdoor. For example, a trigger of sunglasses can mislead a facial recognition model into administrator prediction when any people (source-class-agnostic) or a specific group of people (source-class-specific) wear sunglasses. Existing defense strategies overwhelmingly focus on countering VCB attacks, especially those that are source-class-agnostic. This narrow focus neglects the potential threat of other simpler yet general backdoor types, leading to false security implications. It is, therefore, crucial to discover and elucidate unknown backdoor types, particularly those that can be easily implemented, as a mandatory step before developing countermeasures. This study introduces a new, simple, and general type of backdoor attack coined as the horizontal class backdoor (HCB) that trivially breaches the class dependence characteristic of the VCB, bringing a fresh perspective to the community. HCB is now activated when the trigger is presented together with an innocuous feature, regardless of class. For example, the facial recognition model misclassifies a person who wears sunglasses with a smiling innocuous feature into the targeted person, such as an administrator, regardless of which person. Smiling is innocuous because it is irrelevant to the main task of facial recognition. The key is that these innocuous features (such as rain, fog, or snow in autonomous driving or facial expressions like smiling or sadness in facial recognition) are horizontally shared among classes but are

For agents

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

get_harvested_code_for_paper("2310.00542")
get_code_for_paper("2310.00542")
have("2310.00542")

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

curl https://syntology.ai/api/ran/2310.00542.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.00542.svg)](https://syntology.ai/paper/2310.00542)

Connect an agent — have() is free.