Paper Citation Record · LEDGER

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack

As of 10 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 0 inbound Pith citation observations for arXiv:2507.14248.

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

pith.paper-citation-record.v1
2507.14248 v1

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T16:25:09.024202Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+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

42 of 42 outbound references displayed

verified exact0
verified fuzzy36
unresolved6
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6aedcbf2-12b3-4726-9e06-28b3d05f7305 · outbound

This paper cites Advedge: Optimizing adversarial perturba- tions against interpretable deep learning.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Advedge: Optimizing adversarial perturba- tions against interpretable deep learning

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.767939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d66aa820-63ee-451f-9b4a-92f829c79d7e · outbound

This paper cites Singleadv: single-class target- specific attack against interpretable deep learning systems.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Singleadv: single-class target- specific attack against interpretable deep learning systems

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.753230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 661aaef4-ed68-4bf5-80ed-b1df4a65bd9d · outbound

This paper cites Woo, Eric Chan-Tin, and Tamer Abuhmed.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Woo, Eric Chan-Tin, and Tamer Abuhmed

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.737581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6669e35d-84a8-4088-923c-cbebf46500c5 · outbound

This paper cites Stealthy query-efficient opaque attack against interpretable deep learning.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Stealthy query-efficient opaque attack against interpretable deep learning

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.720625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a9addeae-0b67-4a4f-9882-9501e0868ed7 · outbound

This paper cites Characterizing the risk of fairwashing.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Characterizing the risk of fairwashing

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.704636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6c90bbef-7e59-440a-af95-e11f59fa683c · outbound

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

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Square attack: a query-efficient black-box adversarial attack via random search

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.687960Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c860ae16-543e-40d6-8f42-a81df4cf2b63 · outbound

This paper cites Explainable artificial intelligence (xai): Concepts, taxonomies, opportunities and challenges toward responsible ai.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Explainable artificial intelligence (xai): Concepts, taxonomies, opportunities and challenges toward responsible ai

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.673617Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1cb6ffc9-d4b1-4427-b3f1-3dea75378976 · outbound

This paper cites On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.659073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e84159d9-2147-4bac-ada2-f74a202f08c1 · outbound

This paper cites Evolutionary algorithms in theory and practice: evolu- tion strategies, evolutionary programming, genetic algorithms.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Evolutionary algorithms in theory and practice: evolu- tion strategies, evolutionary programming, genetic algorithms

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.642335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3d9e30e3-4383-42fa-894f-8435e41b5728 · outbound

This paper cites Manipulating shap via adversarial data perturbations (student abstract).

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Manipulating shap via adversarial data perturbations (student abstract)

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.626382Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 067c16d5-9cd4-4564-a1d9-e0c3b1f8ad15 · outbound

This paper cites Understanding robustness of transformers for image classification.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Understanding robustness of transformers for image classification

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.609470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 238990cd-b064-4fbf-8f22-b82c16c6fb62 · outbound

This paper cites Transformer interpretability beyond attention visualization.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Transformer interpretability beyond attention visualization

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.594018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 735b63a9-9cb9-4ede-a5b9-5ce74a8d2d7f · outbound

This paper cites Poba-ga: Perturbation optimized black-box adversarial attacks via genetic algorithm.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Poba-ga: Perturbation optimized black-box adversarial attacks via genetic algorithm

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.578729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 174a26bb-ac95-484b-a020-15f8ba7c0bcd · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack An image is worth 16x16 words: Transformers for image recognition at scale

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.563491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 294333f6-04de-427a-b647-b6e0bca1da58 · outbound

This paper cites Interpretation of neural networks is fragile.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Interpretation of neural networks is fragile

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.542656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 34f905c9-29e2-49cb-9003-bfc7788b9444 · outbound

This paper cites The microbial genetic algorithm.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack The microbial genetic algorithm

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.524043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e65d3fcb-feed-4283-88f5-9546578d345c · outbound

This paper cites Fooling neural network interpretations via adversarial model manipulation.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Fooling neural network interpretations via adversarial model manipulation

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.507760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 455cbfd3-ff9b-44a9-a1d2-36365ec4a346 · outbound

This paper cites Erosion attack: Harness- ing corruption to improve adversarial examples.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Erosion attack: Harness- ing corruption to improve adversarial examples

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.488511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a29cbee4-7348-4d59-885f-b4c3ac26efd4 · outbound

This paper cites Perceiver IO: A General Architecture for Structured Inputs & Outputs.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Perceiver IO: A General Architecture for Structured Inputs & Outputs

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:08.917998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c339e775-8939-4198-9271-a3bd58314b45 · outbound

This paper cites Tracking with saliency region transformer.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Tracking with saliency region transformer

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.467837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation acb09d20-4ad3-4b15-a2ba-0bf18b4f27e7 · outbound

This paper cites Swin transformer: Hierarchical vision transformer using shifted windows.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Swin transformer: Hierarchical vision transformer using shifted windows

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.440482Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d33e15f5-1241-4360-909e-937c5f29ddc9 · outbound

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

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Towards Deep Learning Models Resistant to Adversarial Attacks

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:08.931485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c191231-bc81-4326-920b-12821fdb2ca1 · outbound

This paper cites Explaining nonlinear classification decisions with deep taylor decomposition.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Explaining nonlinear classification decisions with deep taylor decomposition

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.424610Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 53799bf7-4b4c-4b00-9d59-08ad5faf915a · outbound

This paper cites On improving adversarial transferability of vision transformers.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack On improving adversarial transferability of vision transformers

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.408782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e578f807-57cf-40e1-a64f-d9cba8221a27 · outbound

This paper cites Sok: Explainable machine learning in adversarial environments.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Sok: Explainable machine learning in adversarial environments

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.390609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5493ca6a-7ce4-4960-8222-62a0076a26af · outbound

This paper cites Ia-red2: Interpretability-aware redundancy reduction for vision transformers.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Ia-red2: Interpretability-aware redundancy reduction for vision transformers

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.372761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f16a6eeb-e01e-48a4-a872-ff716ebe783e · outbound

This paper cites On the Adversarial Robustness of Vision Transformers.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack On the Adversarial Robustness of Vision Transformers

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:08.955428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f9c62cc-75ef-4dfc-87a6-c8ec198bcd1c · outbound

This paper cites Decision-based query efficient adversarial attack via adaptive boundary learning.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Decision-based query efficient adversarial attack via adaptive boundary learning

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.356621Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6ef1b5b1-61cf-4587-b56a-47130fbbdf93 · outbound

This paper cites Poisoning attacks on algorithmic fairness.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Poisoning attacks on algorithmic fairness

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.339165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4b8d0dcc-5bd5-43ff-8275-f5fd0f979e93 · outbound

This paper cites On single-model transferable targeted attacks: A closer look at decision- level optimization.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack On single-model transferable targeted attacks: A closer look at decision- level optimization

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.321729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 273d4f82-4b6b-4e51-bb8f-5d2dd48d4995 · outbound

This paper cites Efficientnet: Rethinking model scaling for convolutional neural networks.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Efficientnet: Rethinking model scaling for convolutional neural networks

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.305891Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 30a588b2-bcce-4257-be14-444c4ad59877 · outbound

This paper cites Training data-efficient image transformers & distillation through attention.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Training data-efficient image transformers & distillation through attention

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.287515Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 54965bb5-4177-4627-a2b9-ea79e41ff24b · outbound

This paper cites Im- proving transferability of universal adversarial perturbation with feature disruption.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Im- proving transferability of universal adversarial perturbation with feature disruption

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.271880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 37863029-2be6-4811-84e7-1bc7d5da5a17 · outbound

This paper cites Interpretability is a kind of safety: An interpreter-based ensemble for adversary defense.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Interpretability is a kind of safety: An interpreter-based ensemble for adversary defense

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.255905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c41a62a9-1e81-4686-a2b1-0cb4f70a57b4 · outbound

This paper cites Image quality assessment: from error visibility to structural similarity.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Image quality assessment: from error visibility to structural similarity

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.240312Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 86cac68f-2372-4782-b6e9-db9d14471574 · outbound

This paper cites an unresolved cited work.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-08-06T16:25:09.222515Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d02d0c4f-649d-41b1-87ca-eadde096c214 · outbound

This paper cites SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:09.001151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5da7aead-15a6-426a-acce-e18ca1bc710e · outbound

This paper cites Tay, Jiashi Feng, and Shuicheng Yan.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Tay, Jiashi Feng, and Shuicheng Yan

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.203346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 31392a79-5b7f-4c28-a1fa-da5d0a810edc · outbound

This paper cites Towards black-box adversarial attacks on interpretable deep learning systems.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Towards black-box adversarial attacks on interpretable deep learning systems

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.185333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ec52960b-6394-4ffd-8158-0cb1e4f9c45b · outbound

This paper cites Data poisoning attacks against outcome interpretations of predictive models.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Data poisoning attacks against outcome interpretations of predictive models

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.167296Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 075e283d-d795-4327-a10e-66dbde6d533b · outbound

This paper cites an unresolved cited work.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-08-06T16:25:09.151671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 38443bdb-c1e3-4a1b-829b-f5adeb5a3a87 · outbound

This paper cites Interpretable deep learning under fire.

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack Interpretable deep learning under fire

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:09.134431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Pith citing papers

No inbound Pith citation observations are available.