SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.03110 · 2023

RobArch: Designing Robust Architectures against Adversarial Attacks

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 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; 0 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/2301.03110.json · badge: /api/ran/2301.03110.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
shengyun-peng/robarch canonical (classifier label)
classifier basis not recorded on the link
2 ran · 1 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
shengyun-peng/robarch/robustarch/utils.py
code served (permissive licence) · get_code("b0fec41d8eef1acd")
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 list, 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

torch.manual_seed(0)

# Create small tensors for testing
batch_size = 2
num_classes = 4

# output: predictions from model, shape (batch_size, num_classes)
# These are logits/scores for each class
output = torch.randn(batch_size, num_classes)

# target: ground truth class indices, shape (batch_size,)
# Values should be in range [0, num_classes)
target = torch.tensor([0, 2])

# topk: tuple of k values to compute accuracy for
topk = (1, 2)

ARGS = {
    "output": output,
    "target": target,
    "topk": topk,
}
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 list, ndim 1, dtype family float — a list 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
configure_optimizers Ran
ran; our contract draft was wrong, not the code
shengyun-peng/robarch/robustarch/utils.py
code served (permissive licence) · get_code("d9f8f64596cdbaa7")
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 list, 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 as nn

torch.manual_seed(0)

# Build a small model with various parameter types that will exercise
# the configure_optimizers function
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        # Regular linear layer (has weight and bias)
        self.linear = nn.Linear(4, 3)
        
        # BatchNorm2d (should not decay its weight)
        self.bn = nn.BatchNorm2d(3)
        
        # LayerNorm (should not decay its weight)
        self.ln = nn.LayerNorm(4)
        
        # PSiLU (should not decay its alpha parameter)
        self.psilu = nn.Sequential(
            nn.Linear(4, 4),
            PSiLU(alpha=1.0)
        )
        
        # PSSiLU (should not decay its parameters)
        self.pssilu = nn.Sequential(
            nn.Linear(4, 4),
            PSSiLU(alpha=1.0, beta=0.0001)
        )

class PSiLU(nn.Module):
    def __init__(self, alpha: float=1.0, device=None, dtype=None) -> None:
        super().__init__()
        factory_kwargs = {'device': device, 'dtype': dtype}
        self.alpha = nn.Parameter(torch.empty(1, **factory_kwargs).fill_(alpha))

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        return x * torch.sigmoid(self.alpha * x)

class PSSiLU(nn.Module):
    def __init__(self, alpha: float=1.0, beta: float=0.0001, device=None, dtype=None) -> None:
        super().__init__()
        factory_kwargs = {'device': device, 'dtype': dtype}
        self.alpha = nn.Parameter(torch.empty(1, **factory_kwargs).fill_(alpha))
        self.beta = nn.Parameter(torch.empty(1, **factory_kwargs).fill_(beta))

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        self.beta.data = torch.clamp(self.beta.data, 0.0, 1.0)
        return x * (torch.sigmoid(self.alpha * x) - self.beta) / (1.0 - self.beta + 1e-06)

# Create model instance
model = SimpleModel()

ARGS = {
    'model': model
}
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 list, ndim 1, dtype family float — a list 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
get_cifar10 Not yet run
unverified (harvested, no recorded run)
shengyun-peng/robarch/robustarch/utils.py
code served (permissive licence) · get_code("782bf0b123fbfb08")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 later) and 0 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
accuracy 1 other paper
1 later
2308.16258 (2023-08)
Robust Principles: Architectural Design Principles for Adversarially Robust CNNs
configure_optimizers 1 other paper
1 later
2308.16258 (2023-08)
Robust Principles: Architectural Design Principles for Adversarially Robust CNNs
get_cifar10 1 other paper
1 later
2308.16258 (2023-08)
Robust Principles: Architectural Design Principles for Adversarially Robust CNNs

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

Adversarial Training is the most effective approach for improving the robustness of Deep Neural Networks (DNNs). However, compared to the large body of research in optimizing the adversarial training process, there are few investigations into how architecture components affect robustness, and they rarely constrain model capacity. Thus, it is unclear where robustness precisely comes from. In this work, we present the first large-scale systematic study on the robustness of DNN architecture components under fixed parameter budgets. Through our investigation, we distill 18 actionable robust network design guidelines that empower model developers to gain deep insights. We demonstrate these guidelines' effectiveness by introducing the novel Robust Architecture (RobArch) model that instantiates the guidelines to build a family of top-performing models across parameter capacities against strong adversarial attacks. RobArch achieves the new state-of-the-art AutoAttack accuracy on the RobustBench ImageNet leaderboard. The code is available at $\href{https://github.com/ShengYun-Peng/RobArch}{\text{this url}}$.

For agents

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

get_harvested_code_for_paper("2301.03110")
get_code_for_paper("2301.03110")
have("2301.03110")

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

curl https://syntology.ai/api/ran/2301.03110.json

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

[![Syntology run record](https://syntology.ai/api/ran/2301.03110.svg)](https://syntology.ai/paper/2301.03110)

Connect an agent — have() is free.