Paper Citation Record · LEDGER

How Do Diffusion Models Improve Adversarial Robustness?

As of 8 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 0 inbound Pith citation observations for arXiv:2505.22839.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2505.22839 v1

Coverage vector

measured 27 of 27 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:05:49.835754Z

measured 27 of 27 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

27 of 27 outbound references displayed

verified exact3
verified fuzzy7
unresolved16
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a65184a9-63b5-4aed-aa85-b411c6ed2c08 · outbound

This paper cites E Broader impact This paper discusses how and how well do diffusion models actually improve robustness.

How Do Diffusion Models Improve Adversarial Robustness? E Broader impact This paper discusses how and how well do diffusion models actually improve robustness

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:50.779822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c1e1c128-f1f0-47e0-9576-6be5b4c64118 · outbound

This paper cites We used the base seeds s= 0,1,2for all experiments.

How Do Diffusion Models Improve Adversarial Robustness? We used the base seeds s= 0,1,2for all experiments

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:51.209670Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 662edc6f-6e09-43a0-b23e-eba03b76f400 · outbound

This paper cites Adversarial Examples Are a Natural Consequence of Test Error in Noise.

How Do Diffusion Models Improve Adversarial Robustness? Adversarial Examples Are a Natural Consequence of Test Error in Noise

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:47.917506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 340b57ae-6be9-4cc3-a6eb-9d8bda223f9d · outbound

This paper cites an unresolved cited work.

How Do Diffusion Models Improve Adversarial Robustness? Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:05:52.090905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 76e0d470-a0c8-4cd6-b151-4cc20488f5ec · outbound

This paper cites Adversarial Guided Diffusion Models for Adversarial Purification.

How Do Diffusion Models Improve Adversarial Robustness? Adversarial Guided Diffusion Models for Adversarial Purification

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:48.191182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ab935a2-e028-458f-8c0f-91769939379f · outbound

This paper cites Practical black-box attacks against machine learning.

How Do Diffusion Models Improve Adversarial Robustness? Practical black-box attacks against machine learning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:48.332038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59c554c1-9003-4baa-a7b7-3538b7bdddc5 · outbound

This paper cites URL https://doi.org/10.21105/joss.02607.

How Do Diffusion Models Improve Adversarial Robustness? URL https://doi.org/10.21105/joss.02607

Reference 11

Resolution: verified exact; doi, observed 2026-08-07T13:05:50.065493Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 508fa389-d736-4d51-9527-7291982e1dbc · outbound

This paper cites Towards the first adversarially robust neural network model on MNIST.

How Do Diffusion Models Improve Adversarial Robustness? Towards the first adversarially robust neural network model on MNIST

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:05:50.285016Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6d5393ef-c7b2-42ad-9cec-11b04a68f7df · outbound

This paper cites Online Adversarial Purification based on Self-Supervision.

How Do Diffusion Models Improve Adversarial Robustness? Online Adversarial Purification based on Self-Supervision

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:48.637283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31ba7a28-d5ad-4533-8fbe-fa6a070fb078 · outbound

This paper cites Guided Diffusion Model for Adversarial Purification.

How Do Diffusion Models Improve Adversarial Robustness? Guided Diffusion Model for Adversarial Purification

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:48.821582Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3433a069-c3c2-42d3-a1fb-9a33bb1b0019 · outbound

This paper cites On the Convergence and Robustness of Adversarial Training.

How Do Diffusion Models Improve Adversarial Robustness? On the Convergence and Robustness of Adversarial Training

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:48.888250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0f2fbc8-4376-4eb8-b10f-42cdc559f27e · outbound

This paper cites Densepure: Understanding diffusion models for adversarial robustness.

How Do Diffusion Models Improve Adversarial Robustness? Densepure: Understanding diffusion models for adversarial robustness

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:52.225096Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4c2d4804-dd46-41fb-96ab-78b8bf40d508 · outbound

This paper cites The purification time steps were kept the same with Nie et al.

How Do Diffusion Models Improve Adversarial Robustness? The purification time steps were kept the same with Nie et al

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:51.807574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4fb99a8c-abf7-4ce5-b59f-ff392cbc67b2 · outbound

This paper cites an unresolved cited work.

How Do Diffusion Models Improve Adversarial Robustness? Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:05:51.671818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0223aeba-e2b6-4928-9d00-3289ac05eafa · outbound

This paper cites Full gradients were calculated for the PGD/PGD-EOT as Lee & Kim (2023) discovered that the approximations methods used in the original DiffPure (Nie et al.,.

How Do Diffusion Models Improve Adversarial Robustness? Full gradients were calculated for the PGD/PGD-EOT as Lee & Kim (2023) discovered that the approximations methods used in the original DiffPure (Nie et al.,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:51.506209Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 39ab9538-458c-46a8-b497-3531d1c49014 · outbound

This paper cites The full gradient of PGD/PGD-EOT is the strongest attack for DiffPure methods according to Lee & Kim (2023) experiments, and is very computationally expensive.

How Do Diffusion Models Improve Adversarial Robustness? The full gradient of PGD/PGD-EOT is the strongest attack for DiffPure methods according to Lee & Kim (2023) experiments, and is very computationally expensive

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:51.370049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6e8ad9e6-4276-4c8d-ab94-f7e921967de0 · outbound

This paper cites an unresolved cited work.

How Do Diffusion Models Improve Adversarial Robustness? Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:05:50.890289Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 12251674-1921-415f-9590-6a0c070b1129 · outbound

This paper cites pushing-away.

How Do Diffusion Models Improve Adversarial Robustness? pushing-away

Reference 300

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T13:05:51.061526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 055c613a-588c-48f3-ba06-c104483562e0 · outbound

This paper cites For CIFAR-10, we subsampled the first 1000 images from the test set.

How Do Diffusion Models Improve Adversarial Robustness? For CIFAR-10, we subsampled the first 1000 images from the test set

Reference 2009

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:51.946105Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation cbc81c76-1f92-41da-815a-04778cd9b6e4 · outbound

This paper cites Towards Deep Neural Network Architectures Robust to Adversarial Examples.

How Do Diffusion Models Improve Adversarial Robustness? Towards Deep Neural Network Architectures Robust to Adversarial Examples

Reference 2014

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:48.074464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 781d85f6-e870-48ba-ad68-031a0b892e95 · outbound

This paper cites On Evaluating Adversarial Robustness.

How Do Diffusion Models Improve Adversarial Robustness? On Evaluating Adversarial Robustness

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:47.647321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef67f529-d726-42b8-b369-9095209760a9 · outbound

This paper cites (Certified!!) Adversarial Robustness for Free!.

How Do Diffusion Models Improve Adversarial Robustness? (Certified!!) Adversarial Robustness for Free!

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:47.704319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 696eda56-d550-4301-8ca4-50cfc21805d7 · outbound

This paper cites RobustBench: a standardized adversarial robustness benchmark.

How Do Diffusion Models Improve Adversarial Robustness? RobustBench: a standardized adversarial robustness benchmark

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:47.796644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88b6d9d5-b578-48d4-b0e8-54d28cc639d7 · outbound

This paper cites advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorch.

How Do Diffusion Models Improve Adversarial Robustness? advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorch

Reference 2021

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:05:50.544098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 092a2c8a-a5df-415a-bdf4-a30fb6979187 · outbound

This paper cites Explaining and Harnessing Adversarial Examples.

How Do Diffusion Models Improve Adversarial Robustness? Explaining and Harnessing Adversarial Examples

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:47.994463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1325ff7-761d-4dbf-897f-743c67ecc851 · outbound

This paper cites Intriguing properties of neural networks.

How Do Diffusion Models Improve Adversarial Robustness? Intriguing properties of neural networks

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:48.716460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8bd2abb-4702-40f8-b536-821bab1adafb · outbound

This paper cites Towards Deep Learning Models Resistant to Adversarial Attacks.

How Do Diffusion Models Improve Adversarial Robustness? Towards Deep Learning Models Resistant to Adversarial Attacks

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:48.253219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.