Paper Citation Record · LEDGER

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy

As of 12 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 2 inbound Pith citation observations for arXiv:2501.09086.

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

pith.paper-citation-record.v1
2501.09086 v1

Coverage vector

measured 40 of 40 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T20:15:02.244110Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-30T22:48:53.926480Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T13:45:45.886005Z

Reference resolution

40 of 40 outbound references displayed

verified exact0
verified fuzzy32
unresolved8
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ac8bc25e-038f-44fa-ac33-1f2dc759b8c2 · outbound

This paper cites Square attack: a query-efficient black-box adversarial attack via random search.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Square attack: a query-efficient black-box adversarial attack via random search

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:03.094948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 7e20896f-a937-4daa-b0e1-eb9280588255 · outbound

This paper cites Obfus- cated gradients give a false sense of security: Circumventing defenses to adversarial examples.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Obfus- cated gradients give a false sense of security: Circumventing defenses to adversarial examples

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:03.068744Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ca002be3-c804-4dda-954d-9f0887df14d8 · outbound

This paper cites Are transformers more robust than cnns? Advances in Neural Information Processing Systems, 34:26831–26843, 2021.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Are transformers more robust than cnns? Advances in Neural Information Processing Systems, 34:26831–26843, 2021

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:03.049872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation f880818a-d3a4-41aa-84db-a113e7311747 · outbound

This paper cites Towards evaluating the robustness of neural networks.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Towards evaluating the robustness of neural networks

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:03.028840Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 9208ca10-8749-47cb-b244-648be0285b50 · outbound

This paper cites Minimally distorted adversarial examples with a fast adaptive boundary attack.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Minimally distorted adversarial examples with a fast adaptive boundary attack

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:03.003942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation bac1af56-b73d-4e88-bb5e-de63f20289d8 · outbound

This paper cites Reliable evalua- tion of adversarial robustness with an ensemble of diverse parameter-free attacks.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Reliable evalua- tion of adversarial robustness with an ensemble of diverse parameter-free attacks

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:02.980457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 3f677c65-a672-4d84-9c2a-c24ee4435f1c · outbound

This paper cites On the connection between adversarial ro- bustness and saliency map interpretability.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy On the connection between adversarial ro- bustness and saliency map interpretability

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:02.960402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 111670ee-291f-482f-845e-06692a7f262b · outbound

This paper cites Cub-200-2011 segmentations, 2022.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Cub-200-2011 segmentations, 2022

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:02.941207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation f78a7551-165b-498f-b67e-65135da74d0a · outbound

This paper cites Adversarial Spheres.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Adversarial Spheres

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T20:15:02.078782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93942ba1-ca4d-4b1c-b313-5723fbbe8cbe · outbound

This paper cites Explaining and Harnessing Adversarial Examples.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Explaining and Harnessing Adversarial Examples

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-10T20:15:02.084393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edbce7f2-e915-4e62-94be-f11781c85c20 · outbound

This paper cites Delving deep into rectifiers: Surpassing human-level per- formance on imagenet classification.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Delving deep into rectifiers: Surpassing human-level per- formance on imagenet classification

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:02.922799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a856cb1b-d8ff-4da2-a2c0-7f91191c54ae · outbound

This paper cites Deep residual learning for image recognition.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Deep residual learning for image recognition

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:02.901189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation fe380880-6dc9-4bbd-bd14-aa12237347bc · outbound

This paper cites Adversarial example defenses: ensembles of weak defenses are not strong.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Adversarial example defenses: ensembles of weak defenses are not strong

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:02.881670Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a581722d-d35c-4970-aa2f-a9659275d7fc · outbound

This paper cites Densely connected convolutional net- works.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Densely connected convolutional net- works

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:02.856429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation aed03174-a5a1-4201-af63-b87683912745 · outbound

This paper cites Adversar- ial examples are not bugs, they are features.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Adversar- ial examples are not bugs, they are features

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:02.829487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 57a4b3a1-2db1-43b3-a9ed-ef718e6ba68d · outbound

This paper cites Deep imitation learning for au- tonomous vehicles based on convolutional neural networks.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Deep imitation learning for au- tonomous vehicles based on convolutional neural networks

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:02.802943Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 5f2b727c-1007-457a-8199-c0673822a003 · outbound

This paper cites Learning multiple layers of features from tiny images.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Learning multiple layers of features from tiny images

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T20:15:02.123562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0217ec9-1ec2-4ea6-9c13-8d436ed94e9e · outbound

This paper cites Towards deep learn- ing models resistant to adversarial attacks.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Towards deep learn- ing models resistant to adversarial attacks

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:02.762774Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 2ee0a0f1-a52a-4dcf-b83f-f81c674b6d7e · outbound

This paper cites International evaluation of an ai system for breast cancer screening.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy International evaluation of an ai system for breast cancer screening

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:02.741004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation d1cbf2ef-cfc3-45c6-8e65-c814f88370e5 · outbound

This paper cites Generating adversar- ial samples in mini-batches may be detrimental to adversar- ial robustness.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Generating adversar- ial samples in mini-batches may be detrimental to adversar- ial robustness

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:02.721492Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 613ee3e3-bcd6-4a67-b05d-e6fa6715bf07 · outbound

This paper cites Overfitting in ad- versarially robust deep learning.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Overfitting in ad- versarially robust deep learning

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:02.700572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation c7ac8bbe-bfd3-4058-9bc2-f02e6aeea719 · outbound

This paper cites Adversarial training for free! Advances in Neural Information Processing Systems , 32, 2019.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Adversarial training for free! Advances in Neural Information Processing Systems , 32, 2019

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:02.670599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation e6721532-040a-4c1d-9c08-164aa39e998f · outbound

This paper cites Learning important features through propagating activation differences.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Learning important features through propagating activation differences

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:02.647584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 3f7f772a-59ac-48b6-afb1-acb951e43cc1 · outbound

This paper cites Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-10T20:15:02.158713Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e50bef3b-88ef-426b-925d-e2fb9a55219e · outbound

This paper cites Striving for Simplicity: The All Convolutional Net.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Striving for Simplicity: The All Convolutional Net

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-10T20:15:02.164434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19387ab7-4800-4478-885c-4c3ac10cff37 · outbound

This paper cites Disentan- gling adversarial robustness and generalization.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Disentan- gling adversarial robustness and generalization

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:02.630443Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation eb1c91b7-7273-444b-ae60-e5fc0dd092a4 · outbound

This paper cites Is robustness the cost of accuracy?– a comprehensive study on the robustness of 18 deep image classification models.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Is robustness the cost of accuracy?– a comprehensive study on the robustness of 18 deep image classification models

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:02.613218Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 1c657d51-e80e-4e5f-9eb2-c5ad9da6179a · outbound

This paper cites Axiomatic attribution for deep networks.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Axiomatic attribution for deep networks

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-10T20:15:02.179476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 140033f3-9dd5-4097-b7e1-d6a0345e2a3c · outbound

This paper cites In- triguing properties of neural networks.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy In- triguing properties of neural networks

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:02.579220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 57fe6045-36a3-46a4-9403-8f18e7781611 · outbound

This paper cites Adversarial training and robustness for multiple perturbations.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Adversarial training and robustness for multiple perturbations

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:02.557737Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a3f0f56c-13f0-4d8a-acde-f08649922647 · outbound

This paper cites Robustness may 9 be at odds with accuracy.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Robustness may 9 be at odds with accuracy

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:02.534697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a586d277-123d-47a9-900a-5328fb0f31ec · outbound

This paper cites The Caltech-UCSD Birds-200- 2011 dataset, 2011.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy The Caltech-UCSD Birds-200- 2011 dataset, 2011

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:02.515906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ca539f72-fffd-4413-ac9b-d0f3b180f0e3 · outbound

This paper cites Fast is better than free: Revisiting adversarial training.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Fast is better than free: Revisiting adversarial training

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:02.498269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 10d1f39c-7224-4010-82f3-1ec785378860 · outbound

This paper cites On the algorith- mic stability of adversarial training.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy On the algorith- mic stability of adversarial training

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:02.480534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation abd159e2-dd40-4494-b43f-22ace83198b9 · outbound

This paper cites Wide Residual Networks.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Wide Residual Networks

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-10T20:15:02.215494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9b1adff-e258-4de4-a1d9-a0dc5acb7b98 · outbound

This paper cites You only propagate once: Accelerat- ing adversarial training via maximal principle.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy You only propagate once: Accelerat- ing adversarial training via maximal principle

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:02.461196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a74d9975-47e3-4c66-bb1d-24280b5ee943 · outbound

This paper cites Theoretically principled trade-off between robustness and accuracy.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Theoretically principled trade-off between robustness and accuracy

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-10T20:15:02.227679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69f6f67d-a4b1-4956-978b-e209f4553697 · outbound

This paper cites Attacks which do not kill training make adversarial learning stronger.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Attacks which do not kill training make adversarial learning stronger

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:02.433630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation aa34063e-4735-4720-b31a-cb57dfbfdc69 · outbound

This paper cites Improving accuracy-robustness trade- off via pixel reweighted adversarial training.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Improving accuracy-robustness trade- off via pixel reweighted adversarial training

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:02.416117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation dd7f3ee3-0496-43d5-8aca-8898ef5e1995 · outbound

This paper cites Understanding the robustness in vision transformers.

Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy Understanding the robustness in vision transformers

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:15:02.396317Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Pith citing papers

Observation a9a437b6-98e7-496f-b6ea-b7e667d69798 · inbound

Robust Biomedical Publication Type and Study Design Classification with Knowledge-Guided Perturbations cites this paper.

Robust Biomedical Publication Type and Study Design Classification with Knowledge-Guided Perturbations Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-13T02:27:07.550107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 0f293f2d-42d3-47fb-a6ea-c539f01b63cb · inbound

Robust Biomedical Publication Type and Study Design Classification with Knowledge-Guided Perturbations cites this paper.

Robust Biomedical Publication Type and Study Design Classification with Knowledge-Guided Perturbations Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-07-01T13:45:45.887714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.