SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.14347 · 2021

Combating Adversaries with Anti-Adversaries

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 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/2103.14347.json · badge: /api/ran/2103.14347.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
MotasemAlfarra/Combating-Adversaries-with-Anti-Adversaries canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
FunctionStatusWhere it lives
copy_pretrained_model Ran
ran; our contract draft was wrong, not the code
MotasemAlfarra/Combating-Adversaries-with-Anti-Adversaries/experiments/imagenet_pretraining.py
code served (permissive licence) · get_code("51306e7d58858031")
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 SimpleModel. 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 tempfile
import os

torch.manual_seed(0)

# Create a small model to use as the target model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc1 = nn.Linear(4, 8)
        self.fc2 = nn.Linear(8, 3)
    
    def forward(self, x):
        x = self.fc1(x)
        x = self.fc2(x)
        return x

# Create the target model
model = SimpleModel()

# Create a pretrained state dict
pretrained_state_dict = {
    'fc1.weight': torch.randn(8, 4),
    'fc1.bias': torch.randn(8),
    'fc2.weight': torch.randn(3, 8),
    'fc2.bias': torch.randn(3),
}

# Create a temporary file to save the pretrained model
temp_dir = tempfile.gettempdir()
pretrained_path = os.path.join(temp_dir, 'pretrained_test.pt')

# Save the pretrained state dict wrapped in a dict with 'state_dict' key
torch.save({'state_dict': pretrained_state_dict}, pretrained_path)

ARGS = {
    'model': model,
    'path_to_copy_from': pretrained_path,
}
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 SimpleModel — a SimpleModel output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModel 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
filter_state_dict Ran
ran; our contract draft was wrong, not the code
MotasemAlfarra/Combating-Adversaries-with-Anti-Adversaries/experiments/adv_weight_pert.py
pointer only (licence: MIT); the stored copy get_code serves, from inspire-group/variation-regularization, is pointer only (licence: NONE) · get_code("18b797b7c88af64d")
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 inspire-group/variation-regularization, 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.

get_clean_acc Ran
ran, honoured the contract we drafted
MotasemAlfarra/Combating-Adversaries-with-Anti-Adversaries/utils.py
code served (permissive licence) · get_code("b520f828a2f33415")
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. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Define a simple model that takes input and produces classification output
class SimpleModel(nn.Module):
    def __init__(self, input_dim=4, num_classes=3):
        super().__init__()
        self.linear = nn.Linear(input_dim, num_classes)
    
    def forward(self, x):
        return self.linear(x)

# Create model instance
model = SimpleModel(input_dim=4, num_classes=3)

# Create a simple test loader as a list of (X, y) tuples
# Batch size 2, input dimension 4, 3 classes
testloader = [
    (torch.randn(2, 4), torch.tensor([0, 1])),
    (torch.randn(2, 4), torch.tensor([2, 0])),
]

# Device (CPU only)
device = 'cpu'

ARGS = {
    'model': model,
    'testloader': testloader,
    'device': device,
}
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
get_data_utils Not yet run
unverified (harvested, no recorded run)
MotasemAlfarra/Combating-Adversaries-with-Anti-Adversaries/utils.py
code served (permissive licence) · get_code("11d231d3766aa51d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

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

FunctionAlso present inEarliest-datedOthers named
filter_state_dict 5 other papers
5 later
2107.14110 (2021-07)
Enhancing Adversarial Robustness via Test-time Transformation Ensembling
2204.13779 (2022-04)
Formulating Robustness Against Unforeseen Attacks
2206.08675 (2022-06)
Understanding Robust Overfitting of Adversarial Training and Beyond
and 2 more not named here

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

Repositories linked to this paper

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

Abstract

Deep neural networks are vulnerable to small input perturbations known as adversarial attacks. Inspired by the fact that these adversaries are constructed by iteratively minimizing the confidence of a network for the true class label, we propose the anti-adversary layer, aimed at countering this effect. In particular, our layer generates an input perturbation in the opposite direction of the adversarial one and feeds the classifier a perturbed version of the input. Our approach is training-free and theoretically supported. We verify the effectiveness of our approach by combining our layer with both nominally and robustly trained models and conduct large-scale experiments from black-box to adaptive attacks on CIFAR10, CIFAR100, and ImageNet. Our layer significantly enhances model robustness while coming at no cost on clean accuracy.

For agents

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

get_harvested_code_for_paper("2103.14347")
get_code_for_paper("2103.14347")
have("2103.14347")

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

curl https://syntology.ai/api/ran/2103.14347.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.14347.svg)](https://syntology.ai/paper/2103.14347)

Connect an agent — have() is free.