SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1905.11971 · 2019

ME-Net: Towards Effective Adversarial Robustness with Matrix Estimation

arXiv · PDF · Open in the Atlas

Code that ran

2 of 5 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, 1 violated it and 0 have no contract verdict; 1 failure of our instrument; 3 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/1905.11971.json · badge: /api/ran/1905.11971.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
YyzHarry/ME-Net canonical (classifier label)
classifier basis: classifier_2025
2 ran · 3 no recorded run
FunctionStatusWhere it lives
target_transform Ran
ran, violated the contract we drafted
YyzHarry/ME-Net/attack_blackbox.py
code served (permissive licence) · get_code("908e7e3772392464")
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 1, dtype family int, shape (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 numpy as np
import torch

torch.manual_seed(0)

# The function takes a single parameter 'label'
# It converts it to a numpy array, then to a torch tensor with long dtype
# We need to provide a label that can be converted to numpy array

# Create a simple label - can be a list, tuple, or array-like
label_value = [1, 2, 3, 0]

ARGS = {
    "label": label_value
}
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 Tensor, ndim 1, dtype family int, shape (4,) — shape (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
unpickle Ran
ran; our contract draft was wrong, not the code
YyzHarry/ME-Net/attack_blackbox.py
code served (permissive licence) · get_code("80b795d920e2967a")
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 dict. 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 tempfile
import os

# Create a temporary pickle file with sample data
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test.pkl")

# Create sample data to pickle
sample_data = {
    b'key1': b'value1',
    b'key2': [1, 2, 3],
    b'key3': {'nested': b'data'}
}

# Write the pickle file
with open(temp_file, 'wb') as f:
    pickle.dump(sample_data, f)

# Define ARGS for the unpickle function
ARGS = {
    'file': temp_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
nuclear_norm_solve Not yet run
unverified (harvested, no recorded run)
YyzHarry/ME-Net/train_pure.py
code served (permissive licence) · get_code("71fe542d64f2d418")
How it ran

no invocation recorded.

nucnorm Not yet run
unverified (harvested, no recorded run)
YyzHarry/ME-Net/train_pure.py
code served (permissive licence) · get_code("8d121f6d045143a1")
How it ran

no invocation recorded.

usvt Not yet run
unverified (harvested, no recorded run)
YyzHarry/ME-Net/train_pure.py
code served (permissive licence) · get_code("f15d1bdad7f1e1eb")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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 4 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
unpickle 1 other paper
1 later
2203.12691 (2022-03)
Learning to generate line drawings that convey geometry and semantics

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 adversarial attacks. The literature is rich with algorithms that can easily craft successful adversarial examples. In contrast, the performance of defense techniques still lags behind. This paper proposes ME-Net, a defense method that leverages matrix estimation (ME). In ME-Net, images are preprocessed using two steps: first pixels are randomly dropped from the image; then, the image is reconstructed using ME. We show that this process destroys the adversarial structure of the noise, while re-enforcing the global structure in the original image. Since humans typically rely on such global structures in classifying images, the process makes the network mode compatible with human perception. We conduct comprehensive experiments on prevailing benchmarks such as MNIST, CIFAR-10, SVHN, and Tiny-ImageNet. Comparing ME-Net with state-of-the-art defense mechanisms shows that ME-Net consistently outperforms prior techniques, improving robustness against both black-box and white-box attacks.

For agents

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

get_harvested_code_for_paper("1905.11971")
get_code_for_paper("1905.11971")
have("1905.11971")

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

curl https://syntology.ai/api/ran/1905.11971.json

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

[![Syntology run record](https://syntology.ai/api/ran/1905.11971.svg)](https://syntology.ai/paper/1905.11971)

Connect an agent — have() is free.