SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1906.11667 · 2019

Evolving Robust Neural Architectures to Defend from Adversarial Attacks

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 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 1 has no contract verdict; 0 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/1906.11667.json · badge: /api/ran/1906.11667.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
shashankkotyan/RobustArchitectureSearch canonical (classifier label)
classifier basis: census
1 ran · 1 no recorded run
FunctionStatusWhere it lives
build_block Ran
ran on a synthesized input
shashankkotyan/RobustArchitectureSearch/build.py
code served (permissive licence) · get_code("58ff0282ee8b28e9")
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 networkx as nx
import numpy as np

# Create a simple directed graph G with required structure
G = nx.DiGraph()

# Add nodes with proper attributes
# Node 0: input (implicit)
# Node 1: output (GlobalAveragePooling2D)
# Node 2: a convolution layer
# Node 3: a fully connected layer

G.add_node(0, type_layer='input')
G.add_node(1, type_layer='output')
G.add_node(2, type_layer='convolution_2d', layer_params=[16, 3, 3, 1, 1])
G.add_node(3, type_layer='fully_connected', layer_params=[32])

# Add edges to create a valid graph structure
# 0 -> 2 -> 3 -> 1
G.add_edge(0, 2)
G.add_edge(2, 3)
G.add_edge(3, 1)

ARGS = {
    'G': G,
    'num_classes': 10,
    'gpu_index': None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
networkx, numpy, 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
load_data Not yet run
unverified (harvested, no recorded run)
shashankkotyan/RobustArchitectureSearch/build.py
code served (permissive licence) · get_code("113b61b764190c85")
How it ran

no invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 2 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.

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

Neural networks are prone to misclassify slightly modified input images. Recently, many defences have been proposed, but none have improved the robustness of neural networks consistently. Here, we propose to use adversarial attacks as a function evaluation to search for neural architectures that can resist such attacks automatically. Experiments on neural architecture search algorithms from the literature show that although accurate, they are not able to find robust architectures. A significant reason for this lies in their limited search space. By creating a novel neural architecture search with options for dense layers to connect with convolution layers and vice-versa as well as the addition of concatenation layers in the search, we were able to evolve an architecture that is inherently accurate on adversarial samples. Interestingly, this inherent robustness of the evolved architecture rivals state-of-the-art defences such as adversarial training while being trained only on the non-adversarial samples. Moreover, the evolved architecture makes use of some peculiar traits which might be useful for developing even more robust ones. Thus, the results here confirm that more robust architectures exist as well as opens up a new realm of feasibilities for the development and exploration of neural networks. Code available at http://bit.ly/RobustArchitectureSearch.

For agents

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

get_harvested_code_for_paper("1906.11667")
get_code_for_paper("1906.11667")
have("1906.11667")

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

curl https://syntology.ai/api/ran/1906.11667.json

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

[![Syntology run record](https://syntology.ai/api/ran/1906.11667.svg)](https://syntology.ai/paper/1906.11667)

Connect an agent — have() is free.