SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2311.16124 · NeurIPS · 2023

DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification

U Berkeley, Bo Li, Mintong Kang

arXiv · PDF · Open in the Atlas

Code that ran

18 of 24 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, 1 violated it and 0 have no contract verdict; 15 failures of our instrument; 6 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/2311.16124.json · badge: /api/ran/2311.16124.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
kangmintong/DiffAttack canonical (classifier label)
classifier basis not recorded on the link
16 ran · 2 no recorded run
WindVChen/DiffAttack canonical (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
kangmintong/diffattack community
Papers with Code archive
0 ran · 3 no recorded run
FunctionStatusWhere it lives
Normalize Ran
ran; our contract draft was wrong, not the code
kangmintong/DiffAttack/DiffAttack_DDPM_Based/ddpm/unet_ddpm.py
pointer only (licence: NONE); the stored copy get_code serves, from Xingyu-Zheng/BiDM, is pointer only (licence: NONE) · get_code("c3a6b977022957cb")
How it ran

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

approx_standard_normal_cdf Ran
ran; our contract draft was wrong, not the code
kangmintong/DiffAttack/DiffAttack_DDPM_Based/guided_diffusion/losses.py
pointer only (licence: NONE); the stored copy get_code serves, from quandao10/slct, is pointer only (licence: NONE) · get_code("cfd76fd0d89574a4")
How it ran

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

compute_n_params Ran
ran; our contract draft was wrong, not the code
kangmintong/DiffAttack/DiffAttack_Score_Based/utils.py
pointer only (licence: NONE) · get_code("ad12a494674d23fb")
How it ran

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

dict2namespace Ran
ran; our contract draft was wrong, not the code
kangmintong/DiffAttack/DiffAttack_Score_Based/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from leaveslei/obd, is pointer only (licence: NONE) · get_code("bd1f17e427bf51a5")
How it ran

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

discretized_gaussian_log_likelihood Ran
ran; our contract draft was wrong, not the code
kangmintong/DiffAttack/DiffAttack_DDPM_Based/guided_diffusion/losses.py
pointer only (licence: NONE); the stored copy get_code serves, from quandao10/slct, is pointer only (licence: NONE) · get_code("cd33283d615fb3d7")
How it ran

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

encoder Ran
ran; our contract draft was wrong, not the code
WindVChen/DiffAttack/diff_latent_attack.py
code served (permissive licence) · get_code("ecfdcb7de66cc30f")
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 4, dtype family float; no output shape is stated. 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 and ndim 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 numpy as np
from PIL import Image
from unittest.mock import Mock, MagicMock

torch.manual_seed(0)

# Create a minimal mock model with the required VAE structure
class MockLatentDist:
    def sample(self, generator=None):
        # Return a tensor with shape (1, 4, 64, 64) for latent space
        return torch.randn(1, 4, 64, 64)

class MockVAE:
    def encode(self, image):
        mock_output = Mock()
        mock_output.latent_dist = MockLatentDist()
        return mock_output

class MockModel(torch.nn.Module):
    def __init__(self):
        super().__init__()
        self.vae = MockVAE()

# Create a small test image (RGB, 256x256)
test_image = Image.new('RGB', (256, 256), color=(100, 150, 200))

# Create the model
model = MockModel()

ARGS = {
    'image': test_image,
    'model': model,
    'res': 512
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
PIL, 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 4, dtype family float — no output shape is stated: observe_signature.py could not observe it (call:AssertionError)
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
get_optimizer Ran
ran; our contract draft was wrong, not the code
kangmintong/DiffAttack/DiffAttack_DDPM_Based/score_sde/losses.py
pointer only (licence: NONE); the stored copy get_code serves, from hfmei/idc, is pointer only (licence: NONE) · get_code("8ff7c24dade9904c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kangmintong/DiffAttack 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_sde_loss_fn Ran
ran; our contract draft was wrong, not the code
kangmintong/DiffAttack/DiffAttack_DDPM_Based/score_sde/losses.py
pointer only (licence: NONE); the stored copy get_code serves, from hfmei/idc, is pointer only (licence: NONE) · get_code("fac494cec4301110")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kangmintong/DiffAttack 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_timestep_embedding Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
kangmintong/DiffAttack/DiffAttack_DDPM_Based/ddpm/unet_ddpm.py
pointer only (licence: NONE) · get_code("cb49209c125de1b4")
How it ran

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

lerp_clip Ran
ran; our contract draft was wrong, not the code
kangmintong/DiffAttack/DiffAttack_DDPM_Based/classifiers/attribute_net.py
pointer only (licence: NONE); the stored copy get_code serves, from hfmei/idc, is pointer only (licence: NONE) · get_code("195d635db8eb778b")
How it ran

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

max_res_from_state_dict Ran
ran, honoured the contract we drafted
kangmintong/DiffAttack/DiffAttack_DDPM_Based/classifiers/attribute_net.py
pointer only (licence: NONE); the stored copy get_code serves, from hfmei/idc, is pointer only (licence: NONE) · get_code("d5eb57879ef1704e")
How it ran

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

nonlinearity Ran
ran; our contract draft was wrong, not the code
kangmintong/DiffAttack/DiffAttack_DDPM_Based/ddpm/unet_ddpm.py
pointer only (licence: NONE) · get_code("3137073275f8c21a")
How it ran

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

normal_kl Ran
ran, honoured the contract we drafted
kangmintong/DiffAttack/DiffAttack_DDPM_Based/guided_diffusion/losses.py
pointer only (licence: NONE); the stored copy get_code serves, from facebookresearch/agrol, is pointer only (licence: NOASSERTION) · get_code("cf2798b666b231ca")
How it ran

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

optimization_manager Ran
ran; our contract draft was wrong, not the code
kangmintong/DiffAttack/DiffAttack_DDPM_Based/score_sde/losses.py
pointer only (licence: NONE); the stored copy get_code serves, from hfmei/idc, is pointer only (licence: NONE) · get_code("366bb8c7035a2fc8")
How it ran

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

preprocess Ran
ran; our contract draft was wrong, not the code
WindVChen/DiffAttack/diff_latent_attack.py
code served (permissive licence) · get_code("fa609ac1c290e653")
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 4, dtype family float; no output shape is stated. 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 and ndim 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
from PIL import Image

torch.manual_seed(0)

# Create a small test image (4x3 RGB)
image_array = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)
image = Image.fromarray(image_array, mode='RGB')

ARGS = {
    'image': image,
    'res': 512
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
PIL, 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 4, dtype family float — no output shape is stated: observe_signature.py could not observe it (call:AssertionError)
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
register_corrector Ran
ran; our contract draft was wrong, not the code
kangmintong/DiffAttack/DiffAttack_DDPM_Based/score_sde/sampling.py
pointer only (licence: NONE) · get_code("a05b1d0cf3f508b4")
How it ran

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

register_predictor Ran
ran; our contract draft was wrong, not the code
kangmintong/DiffAttack/DiffAttack_DDPM_Based/score_sde/sampling.py
pointer only (licence: NONE) · get_code("473066ddf62a075a")
How it ran

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

str2bool Ran
ran, violated the contract we drafted
kangmintong/DiffAttack/DiffAttack_Score_Based/utils.py
pointer only (licence: NONE) · get_code("7c508037b40522af")
How it ran

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

DiffAttack Not yet run
unverified (harvested, no recorded run)
kangmintong/diffattack/DiffAttack_Score_Based/diffattack/DiffAttack.py
pointer only (licence: NONE) · get_code("d84e0830078f5a50")
How it ran

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

check_randomized Not yet run
unverified (harvested, no recorded run)
kangmintong/diffattack/DiffAttack_Score_Based/diffattack/DiffAttack.py
pointer only (licence: NONE) · get_code("8749fc2e6cd3b1c8")
How it ran

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

check_square_sr Not yet run
unverified (harvested, no recorded run)
kangmintong/diffattack/DiffAttack_Score_Based/diffattack/DiffAttack.py
pointer only (licence: NONE) · get_code("2cd3e1d64ab9a5bb")
How it ran

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

ddim_reverse_sample Not yet run
unverified (harvested, no recorded run)
WindVChen/DiffAttack/diff_latent_attack.py
code served (permissive licence) · get_code("f2778069fba3bee4")
How it ran

no invocation recorded.

from_state_dict Not yet run
unverified (harvested, no recorded run)
kangmintong/DiffAttack/DiffAttack_DDPM_Based/classifiers/attribute_net.py
pointer only (licence: NONE); the stored copy get_code serves, from hfmei/idc, is pointer only (licence: NONE) · get_code("0dd156dfa78cac88")
How it ran

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

get_predictor Not yet run
unverified (harvested, no recorded run)
kangmintong/DiffAttack/DiffAttack_DDPM_Based/score_sde/sampling.py
pointer only (licence: NONE) · get_code("a58facb8fe71823a")
How it ran

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

Also present in other papers' code

Of 24 samples lifted from this paper's linked repositories, 24 carry a function identity and 0 do not. Of the 24 distinct functions with an identity, 21 are also present in other papers whose code we hold (19 with at least one paper dated earlier, 8 the same month, 21 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
str2bool 175 other papers
92 dated earlier, 2 the same month, 78 later, 3 same year, order not determinable · 2 only as an assembly brick
1406.6247 (2014-06)
Recurrent Models of Visual Attention
1603.09382 (2016-03)
Deep Networks with Stochastic Depth
1710.10196 (2017-10)
Progressive Growing of GANs for Improved Quality, Stability, and Variation
and 172 more not named here
normal_kl 160 other papers
64 dated earlier, 5 the same month, 89 later, 2 same year, order not determinable · 19 only as an assembly brick
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
and 157 more not named here
nonlinearity 156 other papers
52 dated earlier, 3 the same month, 100 later, 1 same year, order not determinable · 25 only as an assembly brick
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
2106.00132 (2021-06)
On Fast Sampling of Diffusion Probabilistic Models
2106.06819 (2021-06)
D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
and 153 more not named here
approx_standard_normal_cdf 154 other papers
62 dated earlier, 5 the same month, 85 later, 2 same year, order not determinable · 17 only as an assembly brick
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
and 151 more not named here
discretized_gaussian_log_likelihood 128 other papers
62 dated earlier, 5 the same month, 59 later, 2 same year, order not determinable · 16 only as an assembly brick
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
and 125 more not named here
get_timestep_embedding 91 other papers
37 dated earlier, 4 the same month, 49 later, 1 same year, order not determinable · 7 only as an assembly brick
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
2106.00132 (2021-06)
On Fast Sampling of Diffusion Probabilistic Models
2106.06819 (2021-06)
D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
and 88 more not named here
Normalize 90 other papers
41 dated earlier, 3 the same month, 46 later · 32 only as an assembly brick
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
2106.00132 (2021-06)
On Fast Sampling of Diffusion Probabilistic Models
2106.06819 (2021-06)
D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
and 87 more not named here
compute_n_params 29 other papers
14 dated earlier, 15 later
2111.09452 (2021-11)
Open Vocabulary Object Detection with Pseudo Bounding-Box Labels
2211.09790 (2022-11)
ConStruct-VL: Data-Free Continual Structured VL Concepts Learning
2211.13594 (2022-11)
Self-supervised vision-language pretraining for Medical visual question answering
and 26 more not named here
dict2namespace 28 other papers
10 dated earlier, 1 the same month, 17 later
1907.04809 (2019-07)
Variational Autoencoders and Nonlinear ICA: A Unifying Framework
1912.00589 (2019-12)
Flow Contrastive Estimation of Energy-Based Models
2002.11537 (2020-02)
ICE-BeeM: Identifiable Conditional Energy-Based Deep Models Based on Nonlinear ICA
and 25 more not named here
get_predictor 16 other papers
10 dated earlier, 6 later · 1 only as an assembly brick
2006.09011 (2020-06)
Improved Techniques for Training Score-Based Generative Models
2105.14080 (2021-05)
Gotta Go Fast When Generating Data with Score-Based Models
2112.07068 (2021-12)
Score-Based Generative Modeling with Critically-Damped Langevin Diffusion
and 13 more not named here
optimization_manager 16 other papers
10 dated earlier, 5 later, 1 same year, order not determinable
2106.05527 (2021-06)
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
2110.05243 (2021-10)
Score-based diffusion models for accelerated MRI
2205.01490 (2022-05)
Subspace Diffusion Generative Models
and 13 more not named here
get_optimizer 15 other papers
9 dated earlier, 5 later, 1 same year, order not determinable
2110.05243 (2021-10)
Score-based diffusion models for accelerated MRI
2205.01490 (2022-05)
Subspace Diffusion Generative Models
2209.12753 (2022-09)
On Investigating the Conservative Property of Score-Based Generative Models
and 12 more not named here
register_corrector 15 other papers
10 dated earlier, 5 later · 2 only as an assembly brick
2006.09011 (2020-06)
Improved Techniques for Training Score-Based Generative Models
2011.13456 (2020-11)
Score-Based Generative Modeling through Stochastic Differential Equations
2105.14080 (2021-05)
Gotta Go Fast When Generating Data with Score-Based Models
and 12 more not named here
register_predictor 15 other papers
10 dated earlier, 5 later · 2 only as an assembly brick
2006.09011 (2020-06)
Improved Techniques for Training Score-Based Generative Models
2011.13456 (2020-11)
Score-Based Generative Modeling through Stochastic Differential Equations
2105.14080 (2021-05)
Gotta Go Fast When Generating Data with Score-Based Models
and 12 more not named here
lerp_clip 3 other papers
1 dated earlier, 2 later
2205.07460 (2022-05)
Diffusion Models for Adversarial Purification
2401.16352 (2024-01)
Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalization
2408.08502 (2024-08)
Efficient Image-to-Image Diffusion Classifier for Adversarial Robustness
max_res_from_state_dict 3 other papers
1 dated earlier, 2 later
2205.07460 (2022-05)
Diffusion Models for Adversarial Purification
2401.16352 (2024-01)
Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalization
2408.08502 (2024-08)
Efficient Image-to-Image Diffusion Classifier for Adversarial Robustness
ddim_reverse_sample 2 other papers
1 dated earlier, 1 later
2305.08192 (2023-05)
Diffusion Models for Imperceptible and Transferable Adversarial Attack
2601.17388 (2026-01)
ONRW: Optimizing inversion noise for high-quality and robust watermark
encoder 2 other papers
1 dated earlier, 1 later
2305.08192 (2023-05)
Diffusion Models for Imperceptible and Transferable Adversarial Attack
2601.17388 (2026-01)
ONRW: Optimizing inversion noise for high-quality and robust watermark
from_state_dict 2 other papers
2 later
2401.16352 (2024-01)
Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalization
2408.08502 (2024-08)
Efficient Image-to-Image Diffusion Classifier for Adversarial Robustness
preprocess 2 other papers
1 dated earlier, 1 later
2305.08192 (2023-05)
Diffusion Models for Imperceptible and Transferable Adversarial Attack
2601.17388 (2026-01)
ONRW: Optimizing inversion noise for high-quality and robust watermark

Shown: the 20 functions present in the most other papers. 1 more shared functions are not listed 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

Diffusion-based purification defenses leverage diffusion models to remove crafted perturbations of adversarial examples and achieve state-of-the-art robustness. Recent studies show that even advanced attacks cannot break such defenses effectively, since the purification process induces an extremely deep computational graph which poses the potential problem of vanishing/exploding gradient, high memory cost, and unbounded randomness. In this paper, we propose an attack technique DiffAttack to perform effective and efficient attacks against diffusion-based purification defenses, including both DDPM and score-based approaches. In particular, we propose a deviated-reconstruction loss at intermediate diffusion steps to induce inaccurate density gradient estimation to tackle the problem of vanishing/exploding gradients. We also provide a segment-wise forwarding-backwarding algorithm, which leads to memory-efficient gradient backpropagation. We validate the attack effectiveness of DiffAttack compared with existing adaptive attacks on CIFAR-10 and ImageNet. We show that DiffAttack decreases the robust accuracy of models compared with SOTA attacks by over 20% on CIFAR-10 under ℓ ∞ attack (ϵ = 8/255), and over 10% on ImageNet under ℓ ∞ attack (ϵ = 4/255). We conduct a series of ablations studies, and we find 1) DiffAttack with the deviated-reconstruction loss added over uniformly sampled time steps is more effective than that added over only initial/final steps, and 2) diffusion-based purification with a moderate diffusion length is more robust under DiffAttack.

For agents

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

get_harvested_code_for_paper("2311.16124")
get_code_for_paper("2311.16124")
have("2311.16124")

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

curl https://syntology.ai/api/ran/2311.16124.json

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

[![Syntology run record](https://syntology.ai/api/ran/2311.16124.svg)](https://syntology.ai/paper/2311.16124)

Connect an agent — have() is free.