SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.09852 · ECCV · 2022

Scaling Adversarial Training to Large Perturbation Bounds

Gaurang Sriramanan, Sravanti Addepalli, R Venkatesh Babu, Samyak Jain

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 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; 3 honoured the contract we drafted, 0 violated it and 2 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/2210.09852.json · badge: /api/ran/2210.09852.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
val-iisc/OAAT canonical (classifier label)
classifier basis not recorded on the link
7 ran · 1 no recorded run
FunctionStatusWhere it lives
ResNet18 Ran
ran; our contract draft was wrong, not the code
val-iisc/OAAT/models/resnet.py
code served (permissive licence) · get_code("5b31923638042434")
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 ResNet. 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

torch.manual_seed(0)

ARGS = {
    "num_classes": 10
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
WideResNet34 Ran
ran on a synthesized input
val-iisc/OAAT/models/wideresnet.py
code served (permissive licence) · get_code("f847e64ed88ffc03")
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 WideResNet. 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 math

torch.manual_seed(0)

ARGS = {
    "num_classes": 10
}
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 WideResNet — a WideResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a WideResNet 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
create_window Ran
ran, honoured the contract we drafted
val-iisc/OAAT/perceptual_advex/distances.py
pointer only (licence: MIT); the stored copy get_code serves, from erhul/ZeroPur, is pointer only (licence: NONE) · get_code("7fad0aef219ec2a6")
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 erhul/ZeroPur, 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.

diff_in_weights Ran
ran; our contract draft was wrong, not the code
val-iisc/OAAT/utils_awp.py
pointer only (licence: MIT); the stored copy get_code serves, from Alexkael/S2O, is pointer only (licence: NONE) · get_code("4170809219439d13")
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 Alexkael/S2O, 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.

gaussian Ran
ran, honoured the contract we drafted
val-iisc/OAAT/perceptual_advex/distances.py
pointer only (licence: MIT); the stored copy get_code serves, from erhul/ZeroPur, is pointer only (licence: NONE) · get_code("a945dca82afbbec0")
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 erhul/ZeroPur, 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.

normalize_flatten_features Ran
ran, honoured the contract we drafted
val-iisc/OAAT/perceptual_advex/distances.py
pointer only (licence: MIT); the stored copy get_code serves, from erhul/ZeroPur, is pointer only (licence: NONE) · get_code("096fecc8a890169a")
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 erhul/ZeroPur, 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.

use_default Ran
ran on a synthesized input
val-iisc/OAAT/defaults.py
code served (permissive licence) · get_code("ca563345f2d2b46e")
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 Namespace. 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 argparse

torch.manual_seed(0)

# The function use_default takes a single parameter: default_arg
# which is a string that determines which set of default arguments to configure
# Valid values are: 'CIFAR10_RN18', 'CIFAR10_WRN', 'CIFAR100_WRN', etc.

ARGS = {
    'default_arg': 'CIFAR10_RN18'
}
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 Namespace — a Namespace output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Namespace 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
PreActResNet18 Not yet run
unverified (harvested, no recorded run)
val-iisc/OAAT/models/preactresnet.py
code served (permissive licence) · get_code("6720f86e06ca335e")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 2 the same month, 5 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
gaussian 160 other papers
28 dated earlier, 2 the same month, 129 later, 1 same year, order not determinable · 7 only as an assembly brick
1812.11941 (2018-12)
High Quality Monocular Depth Estimation via Transfer Learning
1904.01538 (2019-04)
Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset
1907.11628 (2019-07)
Unsupervised Learning for Optical Flow Estimation Using Pyramid Convolution LSTM
and 157 more not named here
create_window 52 other papers
16 dated earlier, 36 later · 5 only as an assembly brick
1904.01538 (2019-04)
Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset
1907.11628 (2019-07)
Unsupervised Learning for Optical Flow Estimation Using Pyramid Convolution LSTM
2002.11616 (2020-02)
Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution
and 49 more not named here
ResNet18 27 other papers
8 dated earlier, 19 later
1605.07146 (2016-05)
Wide Residual Networks
1901.09847 (2019-01)
Error Feedback Fixes SignSGD and other Gradient Compression Schemes
1910.09652 (2019-10)
Kernelized Wasserstein Natural Gradient
and 24 more not named here
diff_in_weights 7 other papers
2 dated earlier, 2 the same month, 3 later · 1 only as an assembly brick
1901.08573 (2019-01)
Theoretically Principled Trade-off between Robustness and Accuracy
2208.08270 (2022-08)
On the Privacy Effect of Data Enhancement via the Lens of Memorization
2210.03543 (2022-10)
A2: Efficient Automated Attacker for Boosting Adversarial Training
and 4 more not named here
normalize_flatten_features 4 other papers
2 dated earlier, 2 later
2006.12655 (2020-06)
Perceptual Adversarial Robustness: Defense Against Unseen Threat Models
2209.05785 (2022-09)
Adversarial Coreset Selection for Efficient Robust Training
2211.00824 (2022-11)
Adversarial Auto-Augment with Label Preservation: A Representation Learning Principle Guided Approach
and 1 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

The vulnerability of Deep Neural Networks to Adversarial Attacks has fuelled research towards building robust models. While most Adversarial Training algorithms aim at defending attacks constrained within low magnitude Lp norm bounds, real-world adversaries are not limited by such constraints. In this work, we aim to achieve adversarial robustness within larger bounds, against perturbations that may be perceptible, but do not change human (or Oracle) prediction. The presence of images that flip Oracle predictions and those that do not makes this a challenging setting for adversarial robustness. We discuss the ideal goals of an adversarial defense algorithm beyond perceptual limits, and further highlight the shortcomings of naively extending existing training algorithms to higher perturbation bounds. In order to overcome these shortcomings, we propose a novel defense, Oracle-Aligned Adversarial Training (OA-AT), to align the predictions of the network with that of an Oracle during adversarial training. The proposed approach achieves state-of-the-art performance at large epsilon bounds (such as an L-inf bound of 16/255 on CIFAR-10) while outperforming existing defenses (AWP, TRADES, PGD-AT) at standard bounds (8/255) as well.

For agents

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

get_harvested_code_for_paper("2210.09852")
get_code_for_paper("2210.09852")
have("2210.09852")

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

curl https://syntology.ai/api/ran/2210.09852.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.09852.svg)](https://syntology.ai/paper/2210.09852)

Connect an agent — have() is free.