SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2110.14871 · NeurIPS · 2021

Generalized Depthwise-Separable Convolutions for Adversarially Robust and Efficient Neural Networks

Hassan Dbouk, Naresh Shanbhag

arXiv · PDF · Open in the Atlas

Code that ran

7 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (4 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 1 failure of our instrument; 4 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/2110.14871.json · badge: /api/ran/2110.14871.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
hsndbk4/gdws canonical (classifier label)
classifier basis: classifier_2025
5 ran · 3 no recorded run
bethgelab/foolbox canonical (classifier label)
classifier basis not recorded on the link
2 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
0 ran · 1 no recorded run
FunctionStatusWhere it lives
BatchNorm2dStat Ran
ran on a synthesized input · constructed an object; no result was computed
hsndbk4/gdws/archs/robnet/basic_operations.py
pointer only (licence: NONE) · get_code("bbf1434434ea4bef")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hsndbk4/gdws 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.

Conv2dStat Ran
ran on a synthesized input · constructed an object; no result was computed
hsndbk4/gdws/archs/robnet/basic_operations.py
pointer only (licence: NONE) · get_code("ebb64b22c3b7c8d8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hsndbk4/gdws 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.

LEGO Ran
ran; our contract draft was wrong, not the code
hsndbk4/gdws/gdws_utils.py
pointer only (licence: NONE) · get_code("a54eb83659a77bf5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hsndbk4/gdws 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.

LinearStat Ran
ran on a synthesized input · constructed an object; no result was computed
hsndbk4/gdws/archs/robnet/basic_operations.py
pointer only (licence: NONE) · get_code("ad0931d390d6ae0a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hsndbk4/gdws 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.

SepConv Ran
ran on a synthesized input · constructed an object; no result was computed
hsndbk4/gdws/archs/robnet/basic_operations.py
pointer only (licence: NONE) · get_code("fe3d7b3b72919744")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hsndbk4/gdws 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_device Ran
ran on a synthesized input
bethgelab/foolbox/foolbox/models/pytorch.py
code served (permissive licence) · get_code("c7eae778ac0b3cc3")
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 device. 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 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)

# The function get_device takes a device parameter and returns a torch.device
# It handles three cases:
# 1. device is None -> returns cuda:0 if available, else cpu
# 2. device is a string -> converts to torch.device
# 3. device is already a device object -> returns it as-is

# We'll test all three cases by creating multiple ARGS dictionaries
# But since we need a single ARGS dict, we'll provide one representative case

ARGS = {
    'device': None
}
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 device — a device output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a device 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_device Ran
ran on a synthesized input
bethgelab/foolbox/foolbox/models/tensorflow.py
code served (permissive licence) · get_code("f80ad87b3a499407")
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 _EagerDeviceContext. 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

# The function expects a 'device' parameter which can be:
# - None (will default to GPU if available, else CPU)
# - A string (device specification like '/GPU:0' or '/CPU:0')
# - A tf.device object

# Testing with None to let the function decide based on availability
ARGS = {
    'device': None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type _EagerDeviceContext — a _EagerDeviceContext output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a _EagerDeviceContext 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
MEGO Not yet run
unverified (harvested, no recorded run)
hsndbk4/gdws/gdws_utils.py
pointer only (licence: NONE) · get_code("87e4b8ea4c1588d9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hsndbk4/gdws 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.

ModuleStat Not yet run
unverified (harvested, no recorded run)
hsndbk4/gdws/archs/robnet/basic_operations.py
pointer only (licence: NONE) · get_code("ce71e733d8a6259e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hsndbk4/gdws 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.

attack_pgd Not yet run
unverified (harvested, no recorded run)
hsndbk4/gdws/eval_robustness.py
pointer only (licence: NONE) · get_code("5d11d79b4e03238d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hsndbk4/gdws 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.

clamp Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from csdongxian/AWP
pointer only · get_code("8a93e041134b597a")
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. No invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 later) and 10 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
clamp 33 other papers
9 dated earlier, 1 the same month, 23 later · 1 only as an assembly brick
1706.06083 (2017-06)
Towards Deep Learning Models Resistant to Adversarial Attacks
2001.03994 (2020-01)
Fast is better than free: Revisiting adversarial training
2002.11569 (2020-02)
Overfitting in adversarially robust deep learning
and 30 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

Despite their tremendous successes, convolutional neural networks (CNNs) incur high computational/storage costs and are vulnerable to adversarial perturbations. Recent works on robust model compression address these challenges by combining model compression techniques with adversarial training. But these methods are unable to improve throughput (frames-per-second) on real-life hardware while simultaneously preserving robustness to adversarial perturbations. To overcome this problem, we propose the method of Generalized Depthwise-Separable (GDWS) convolution -an efficient, universal, post-training approximation of a standard 2D convolution. GDWS dramatically improves the throughput of a standard pre-trained network on real-life hardware while preserving its robustness. Lastly, GDWS is scalable to large problem sizes since it operates on pre-trained models and doesn't require any additional training. We establish the optimality of GDWS as a 2D convolution approximator and present exact algorithms for constructing optimal GDWS convolutions under complexity and error constraints. We demonstrate the effectiveness of GDWS via extensive experiments on CIFAR-10, SVHN, and ImageNet datasets. Our code can be found at https://github.com/hsndbk4/ GDWS.

For agents

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

get_harvested_code_for_paper("2110.14871")
get_code_for_paper("2110.14871")
have("2110.14871")

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

curl https://syntology.ai/api/ran/2110.14871.json

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

[![Syntology run record](https://syntology.ai/api/ran/2110.14871.svg)](https://syntology.ai/paper/2110.14871)

Connect an agent — have() is free.