SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.00567 · 2023

Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks

arXiv · PDF · Open in the Atlas

Code that ran

16 of 20 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 14 failures 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/2310.00567.json · badge: /api/ran/2310.00567.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
mail-research/randomized_defenses canonical (classifier label)
classifier basis: census
16 ran · 4 no recorded run
FunctionStatusWhere it lives
add_defense Ran
ran; our contract draft was wrong, not the code
mail-research/randomized_defenses/models/utils.py
pointer only (licence: GPL-3.0) · get_code("f80e7f6342bb06ff")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, mail-research/randomized_defenses, is not in the permissive set Syntology serves inline. 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.

create_aa Ran
ran; our contract draft was wrong, not the code
mail-research/randomized_defenses/models/resnet.py
pointer only (licence: GPL-3.0) · get_code("de9aaff4c2936743")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, mail-research/randomized_defenses, is not in the permissive set Syntology serves inline. 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.

defense_token Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
mail-research/randomized_defenses/models/utils.py
pointer only (licence: GPL-3.0) · get_code("d903e362d00e661c")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, mail-research/randomized_defenses, is not in the permissive set Syntology serves inline. 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.

dense_to_onehot Ran
ran; our contract draft was wrong, not the code
mail-research/randomized_defenses/utils.py
pointer only (licence: GPL-3.0); the stored copy get_code serves, from phenetos/calibrationattack, is pointer only (licence: NONE) · get_code("176dfa1e026fb136")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, mail-research/randomized_defenses, is not in the permissive set Syntology serves inline. 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.

downsample_conv Ran
ran; our contract draft was wrong, not the code
mail-research/randomized_defenses/models/resnet.py
pointer only (licence: GPL-3.0) · get_code("eea0376ea397a1c7")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, mail-research/randomized_defenses, is not in the permissive set Syntology serves inline. 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_idx Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
mail-research/randomized_defenses/attack/nes.py
pointer only (licence: GPL-3.0) · get_code("3cb33b36db4150ca")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, mail-research/randomized_defenses, is not in the permissive set Syntology serves inline. 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_margin Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
mail-research/randomized_defenses/attack/nes.py
pointer only (licence: GPL-3.0) · get_code("59a538c2bf7701e7")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, mail-research/randomized_defenses, is not in the permissive set Syntology serves inline. 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_padding Ran
ran, honoured the contract we drafted
mail-research/randomized_defenses/models/resnet.py
pointer only (licence: GPL-3.0); the stored copy get_code serves, from xslidi/EfficientNets_ddl_apex, is pointer only (licence: NONE) · get_code("9b02c1068795fd5b")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, mail-research/randomized_defenses, is not in the permissive set Syntology serves inline. 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.

random_classes_except_current Ran
ran; our contract draft was wrong, not the code
mail-research/randomized_defenses/utils.py
pointer only (licence: GPL-3.0) · get_code("0c48a3a1bc51d3e9")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, mail-research/randomized_defenses, is not in the permissive set Syntology serves inline. 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.

softmax Ran
ran, honoured the contract we drafted
mail-research/randomized_defenses/utils.py
pointer only (licence: GPL-3.0); the stored copy get_code serves, from GEEX-Weixing/PKD, is pointer only (licence: NONE) · get_code("8bf374c9e1999142")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, mail-research/randomized_defenses, is not in the permissive set Syntology serves inline. 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.

tojpeg Ran
ran; our contract draft was wrong, not the code
mail-research/randomized_defenses/models/wrapper.py
pointer only (licence: GPL-3.0) · get_code("e3593b2830ad0418")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, mail-research/randomized_defenses, is not in the permissive set Syntology serves inline. 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.

tv Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
mail-research/randomized_defenses/models/tvm.py
pointer only (licence: GPL-3.0) · get_code("6acddfe42148f8f2")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, mail-research/randomized_defenses, is not in the permissive set Syntology serves inline. 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.

tv_dx Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
mail-research/randomized_defenses/models/tvm.py
pointer only (licence: GPL-3.0) · get_code("13910d402badb827")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, mail-research/randomized_defenses, is not in the permissive set Syntology serves inline. 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.

vanilla_resnet20 Ran
ran; our contract draft was wrong, not the code
mail-research/randomized_defenses/models/vanilla_resnet.py
pointer only (licence: GPL-3.0) · get_code("cd56898dd1531f85")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, mail-research/randomized_defenses, is not in the permissive set Syntology serves inline. 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.

vanilla_resnet32 Ran
ran; our contract draft was wrong, not the code
mail-research/randomized_defenses/models/vanilla_resnet.py
pointer only (licence: GPL-3.0) · get_code("cab91481ef35184c")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, mail-research/randomized_defenses, is not in the permissive set Syntology serves inline. 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.

vanilla_resnet44 Ran
ran; our contract draft was wrong, not the code
mail-research/randomized_defenses/models/vanilla_resnet.py
pointer only (licence: GPL-3.0) · get_code("2acb1379b48508e4")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, mail-research/randomized_defenses, is not in the permissive set Syntology serves inline. 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.

checkpoint_seq Not yet run
unverified (harvested, no recorded run)
mail-research/randomized_defenses/models/robust_vit.py
pointer only (licence: GPL-3.0) · get_code("4e82d32ad5df0e01")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, mail-research/randomized_defenses, is not in the permissive set Syntology serves inline. 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.

create_robust_model Not yet run
unverified (harvested, no recorded run)
mail-research/randomized_defenses/models/utils.py
pointer only (licence: GPL-3.0) · get_code("4f4087e87730c76c")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, mail-research/randomized_defenses, is not in the permissive set Syntology serves inline. 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.

noise_resnet20 Not yet run
unverified (harvested, no recorded run)
mail-research/randomized_defenses/models/noise_resnet.py
pointer only (licence: GPL-3.0) · get_code("45164c859a619736")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, mail-research/randomized_defenses, is not in the permissive set Syntology serves inline. 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.

tv_l2 Not yet run
unverified (harvested, no recorded run)
mail-research/randomized_defenses/models/tvm.py
pointer only (licence: GPL-3.0) · get_code("9c87fc8acd9c2789")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, mail-research/randomized_defenses, is not in the permissive set Syntology serves inline. 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 20 samples lifted from this paper's linked repositories, 20 carry a function identity and 0 do not. Of the 20 distinct functions with an identity, 9 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 2 the same month, 2 later) and 11 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
get_padding 10 other papers
8 dated earlier, 1 the same month, 1 same year, order not determinable
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
2110.07641 (2021-10)
Non-deep Networks
2203.12827 (2022-03)
Sparse Instance Activation for Real-Time Instance Segmentation
and 7 more not named here
downsample_conv 7 other papers
6 dated earlier, 1 the same month
2110.07641 (2021-10)
Non-deep Networks
2203.12827 (2022-03)
Sparse Instance Activation for Real-Time Instance Segmentation
2205.13490 (2022-05)
SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation
and 4 more not named here
dense_to_onehot 3 other papers
2 dated earlier, 1 later
2105.15010 (2021-05)
Query Attack by Multi-Identity Surrogates
2308.11804 (2023-08)
Adversarial Illusions in Multi-Modal Embeddings
2401.02718 (2024-01)
Calibration Attacks: A Comprehensive Study of Adversarial Attacks on Model Confidence
softmax 3 other papers
2 dated earlier, 1 later
2105.15010 (2021-05)
Query Attack by Multi-Identity Surrogates
2308.11804 (2023-08)
Adversarial Illusions in Multi-Modal Embeddings
2510.10116 (2025-10)
Preference-driven Knowledge Distillation for Few-shot Node Classification
create_aa 2 other papers
2 dated earlier · 1 only as an assembly brick
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
2302.12712 (2023-02)
Amortised Invariance Learning for Contrastive Self-Supervision
noise_resnet20 1 other paper
1 dated earlier
1811.09310 (2018-11)
Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial Attack
vanilla_resnet20 1 other paper
1 dated earlier
1811.09310 (2018-11)
Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial Attack
vanilla_resnet32 1 other paper
1 dated earlier
1811.09310 (2018-11)
Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial Attack
vanilla_resnet44 1 other paper
1 dated earlier
1811.09310 (2018-11)
Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial Attack

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

Recent works have shown that deep neural networks are vulnerable to adversarial examples that find samples close to the original image but can make the model misclassify. Even with access only to the model's output, an attacker can employ black-box attacks to generate such adversarial examples. In this work, we propose a simple and lightweight defense against black-box attacks by adding random noise to hidden features at intermediate layers of the model at inference time. Our theoretical analysis confirms that this method effectively enhances the model's resilience against both score-based and decision-based black-box attacks. Importantly, our defense does not necessitate adversarial training and has minimal impact on accuracy, rendering it applicable to any pre-trained model. Our analysis also reveals the significance of selectively adding noise to different parts of the model based on the gradient of the adversarial objective function, which can be varied during the attack. We demonstrate the robustness of our defense against multiple black-box attacks through extensive empirical experiments involving diverse models with various architectures.

For agents

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

get_harvested_code_for_paper("2310.00567")
get_code_for_paper("2310.00567")
have("2310.00567")

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

curl https://syntology.ai/api/ran/2310.00567.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.00567.svg)](https://syntology.ai/paper/2310.00567)

Connect an agent — have() is free.