Paper Citation Record · LEDGER

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments

As of 12 August 2026, this Paper Citation Record lists 57 of 57 outbound references and 4 inbound Pith citation observations for arXiv:2412.00114.

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

pith.paper-citation-record.v1
2412.00114 v2

Coverage vector

measured 57 of 57 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T10:48:46.283268Z

measured 61 of 61 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 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-11T18:24:49.439929Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-20T09:28:10.399987Z

Reference resolution

57 of 57 outbound references displayed

verified exact1
verified fuzzy27
unresolved29
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 959f4d25-889c-4b7e-8222-165a1f45a24e · outbound

This paper cites Un- veiling typographic deceptions: Insights of the typographic vulnerability in large vision-language model.arXiv.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Un- veiling typographic deceptions: Insights of the typographic vulnerability in large vision-language model.arXiv

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:48:48.512263Z

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 42e7d51d-2a0b-47b5-a97f-57815e83a9dc · outbound

This paper cites Vision-LLMs Can Fool Themselves with Self-Generated Typographic Attacks.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Vision-LLMs Can Fool Themselves with Self-Generated Typographic Attacks

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T10:48:44.941580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93cd3123-85b5-4ec7-aff2-0fd7fc026c59 · outbound

This paper cites Learning transferable visual models from natural language supervi- sion.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Learning transferable visual models from natural language supervi- sion

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-12T10:48:44.946224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c5de27f-7e44-42aa-8475-5cb864f2e4c0 · outbound

This paper cites Flamingo: a visual language model for few-shot learning.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Flamingo: a visual language model for few-shot learning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-12T10:48:44.950726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd7e1a67-32cb-4e9e-8dac-39c719987036 · outbound

This paper cites Visual instruction tuning.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Visual instruction tuning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T10:48:44.954832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09c59ec9-9fc4-4daf-b530-db04b9f84557 · outbound

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

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Towards Deep Learning Models Resistant to Adversarial Attacks

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-12T10:48:44.958598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce35016b-867c-45e8-851c-c68f624124e4 · outbound

This paper cites Irad: implicit representation-driven image resampling against adversarial attacks.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Irad: implicit representation-driven image resampling against adversarial attacks

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:48:48.481016Z

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 2d383b11-c351-4d92-ba72-cd6e3a1d9365 · outbound

This paper cites Lrr: Language- driven resamplable continuous representation against adver- sarial tracking attacks.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Lrr: Language- driven resamplable continuous representation against adver- sarial tracking attacks

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:48:48.468554Z

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 b78f2d46-0d51-47ef-9122-d9ed6bb4c198 · outbound

This paper cites On the Robustness of Segment Anything.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments On the Robustness of Segment Anything

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T10:48:44.970401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a4e8087-764a-4fde-ab6b-7e2d6d3dade8 · outbound

This paper cites Adversarial relighting against face recognition.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Adversarial relighting against face recognition

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:48:48.391424Z

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 145a7d42-1fff-401a-a238-e83ccaf636cf · outbound

This paper cites MAGIC: Mastering Physical Adversarial Generation in Context through Collaborative LLM Agents.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments MAGIC: Mastering Physical Adversarial Generation in Context through Collaborative LLM Agents

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-08-12T10:48:46.475722Z

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 3216e681-342c-400c-96e0-d4848e02de32 · outbound

This paper cites ALA: Naturalness-aware Adversarial Lightness Attack.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments ALA: Naturalness-aware Adversarial Lightness Attack

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T10:48:45.066082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac7130ca-b754-4af9-a1ad-cb6de616d5e7 · outbound

This paper cites On evaluating adversarial robustness of large vision-language models.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments On evaluating adversarial robustness of large vision-language models

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:48:48.260042Z

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 f5256f5e-fe27-4a98-bd75-772143bdbc7a · outbound

This paper cites InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T10:48:45.074404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd03d5ca-c492-46a3-89e3-2166e0b99744 · outbound

This paper cites Transferable multimodal attack on vision-language pre-training models.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Transferable multimodal attack on vision-language pre-training models

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:48:48.248497Z

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 c0cdd27f-7577-49e8-84f5-1c4ae4132fa9 · outbound

This paper cites Towards adversarial at- tack on vision-language pre-training models.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Towards adversarial at- tack on vision-language pre-training models

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:48:48.237153Z

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 11faa285-7bac-4ba0-873f-ab61e1f4b131 · outbound

This paper cites Set-level guidance at- tack: Boosting adversarial transferability of vision-language pre-training models.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Set-level guidance at- tack: Boosting adversarial transferability of vision-language pre-training models

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:48:48.101647Z

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 fb43b57d-0e3f-43d5-a6a7-51b8d61b2136 · outbound

This paper cites Boosting transferability in vision-language attacks via diversification along the intersection region of adversarial trajectory.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Boosting transferability in vision-language attacks via diversification along the intersection region of adversarial trajectory

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:48:48.059640Z

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 ffa708c9-3947-4b29-a55c-9cf780b3067a · outbound

This paper cites Towards Transferable Attacks Against Vision-LLMs in Autonomous Driving with Typography.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Towards Transferable Attacks Against Vision-LLMs in Autonomous Driving with Typography

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-12T10:48:45.287680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 474571cb-8333-43b4-815a-9125db1e13e4 · outbound

This paper cites Textdiffuser-2: Unleashing the power of language models for text rendering.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Textdiffuser-2: Unleashing the power of language models for text rendering

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:48:47.997162Z

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 09c6dfb6-7f04-4e80-9e47-3c58018adf70 · outbound

This paper cites An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts on Vision-Language Models.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts on Vision-Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-12T10:48:45.296501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c31f85b-ca59-4af3-b03c-cc86b6626988 · outbound

This paper cites On the robustness of large multimodal mod- els against image adversarial attacks.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments On the robustness of large multimodal mod- els against image adversarial attacks

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:48:47.950273Z

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 e49005a2-0855-4804-b1a8-fc25f761621d · outbound

This paper cites Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-12T10:48:45.365436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7977e5ac-6b8b-49aa-b551-2e6a9470ce12 · outbound

This paper cites Multimodal neurons in artificial neural networks.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Multimodal neurons in artificial neural networks

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-12T10:48:45.385682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f87c4e92-7e62-42c5-b29a-d313afa8ad4a · outbound

This paper cites Blended diffusion for text-driven editing of natural images.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Blended diffusion for text-driven editing of natural images

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-12T10:48:45.389653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7952bc4-54b3-4cea-802d-1ac0f53be564 · outbound

This paper cites Dis- entangling visual and written concepts in clip.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Dis- entangling visual and written concepts in clip

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:48:47.838749Z

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 6695e2fb-87b9-4fa1-98bf-2e5cb403c4c6 · outbound

This paper cites Patching open-vocabulary models by interpolating weights.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Patching open-vocabulary models by interpolating weights

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-12T10:48:45.397035Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60625371-7448-446f-be21-67bd553096ee · outbound

This paper cites Defense-prefix for pre- venting typographic attacks on clip.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Defense-prefix for pre- venting typographic attacks on clip

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:48:47.788280Z

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 070e2b28-f9a3-4f9a-a4c0-fefd294b99b6 · outbound

This paper cites Defending lvlms against vision attacks through partial-perception supervision, 2024.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Defending lvlms against vision attacks through partial-perception supervision, 2024

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:48:47.681126Z

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 cbe3766e-6983-4894-a68a-269518e540d8 · outbound

This paper cites Adversarial Machine Learning at Scale.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Adversarial Machine Learning at Scale

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-12T10:48:45.408168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e34ba8c-1c18-42cf-af62-868a7192a2f2 · outbound

This paper cites Adver- sarial examples in the physical world.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Adver- sarial examples in the physical world

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-12T10:48:45.549168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c0960cc-a898-421b-ba7d-434aa136a5dd · outbound

This paper cites Accessorize to a crime: Real and stealthy attacks on state-of-the-art face recognition.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Accessorize to a crime: Real and stealthy attacks on state-of-the-art face recognition

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:48:47.601997Z

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 acbefc5f-ff81-44d3-b807-6ad022e671fb · outbound

This paper cites Robust physical-world attacks on deep learning visual classification.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Robust physical-world attacks on deep learning visual classification

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:48:47.588605Z

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 2cdecedd-0da2-4719-b7f6-7a826f997784 · outbound

This paper cites Towards transferable targeted 3d adversarial attack in the physical world.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Towards transferable targeted 3d adversarial attack in the physical world

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:48:47.398716Z

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 b3b4cd52-3786-4608-ae85-fbe44f906476 · outbound

This paper cites Adversarial t-shirt! evading person detectors in a physical world.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Adversarial t-shirt! evading person detectors in a physical world

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:48:47.353693Z

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 f3ceabdf-d21f-4450-b350-97bd03b9b2e9 · outbound

This paper cites Fooling thermal infrared pedestrian detectors in real world using small bulbs.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Fooling thermal infrared pedestrian detectors in real world using small bulbs

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:48:47.343421Z

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 2b2d1cd6-6f27-4c9a-9029-48c52e810cef · outbound

This paper cites Infrared invisible clothing: Hiding from infrared detectors at multiple angles in real world.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Infrared invisible clothing: Hiding from infrared detectors at multiple angles in real world

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:48:47.330137Z

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 af9c87b8-c84c-4b71-a13a-e3dc5b7207f4 · outbound

This paper cites Hotcold block: Fooling thermal infrared detectors with a novel wearable design.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Hotcold block: Fooling thermal infrared detectors with a novel wearable design

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:48:47.280549Z

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 69b89cfe-1f66-4efa-affc-6774cc2a4bf3 · outbound

This paper cites Adversarial camouflage: Hiding physical- world attacks with natural styles.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Adversarial camouflage: Hiding physical- world attacks with natural styles

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:48:47.213692Z

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 dc9c1e9a-f670-481d-9cef-c6846de4cbec · outbound

This paper cites Uni- fied adversarial patch for cross-modal attacks in the physical world.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Uni- fied adversarial patch for cross-modal attacks in the physical world

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:48:47.068983Z

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 6b928e87-84ca-4978-ab13-29b03ccb9fdf · outbound

This paper cites Visual instruction tuning, 2023.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Visual instruction tuning, 2023

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:48:47.057281Z

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 1db9c836-f655-43c3-be4d-8e930646beb8 · outbound

This paper cites Making the v in vqa matter: Elevating the role of image understanding in visual question answering.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Making the v in vqa matter: Elevating the role of image understanding in visual question answering

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:48:47.044858Z

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 676dac00-ae12-478b-9c19-07031a83cdb6 · outbound

This paper cites Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-12T10:48:45.715928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3e52cf9-54d1-4c00-9fb4-86d53d62740c · outbound

This paper cites Textdiffuser: Diffusion models as text painters.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Textdiffuser: Diffusion models as text painters

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:48:47.030989Z

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 1e92ab44-e181-4564-93c5-4b565c4bc00c · outbound

This paper cites LingoQA: Visual Question Answering for Autonomous Driving.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments LingoQA: Visual Question Answering for Autonomous Driving

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-12T10:48:45.724257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b04b758-3b03-4cd7-a2ab-a7f3b704e047 · outbound

This paper cites Instructblip: Towards general-purpose vision- language models with instruction tuning, 2023.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Instructblip: Towards general-purpose vision- language models with instruction tuning, 2023

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-12T10:48:45.728189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3541e0bc-722a-44f4-9506-9c0f60ac74cd · outbound

This paper cites MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-12T10:48:45.868817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 833ecf8b-6c0a-45c1-b5a0-0b8c86684a08 · outbound

This paper cites an unresolved cited work.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Unresolved cited work

Reference 48

Resolution: unresolved; raw_fallback, observed 2026-08-12T10:48:46.950480Z

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 a796c973-ab8b-4611-b8f6-56d235886a28 · outbound

This paper cites an unresolved cited work.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Unresolved cited work

Reference 49

Resolution: unresolved; raw_fallback, observed 2026-08-12T10:48:46.937711Z

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 21916217-b062-4b09-aa23-d164e0d419e9 · outbound

This paper cites an unresolved cited work.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Unresolved cited work

Reference 50

Resolution: unresolved; raw_fallback, observed 2026-08-12T10:48:46.879841Z

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 3750fd6c-f257-4ab3-917a-4af553051763 · outbound

This paper cites an unresolved cited work.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Unresolved cited work

Reference 51

Resolution: unresolved; raw_fallback, observed 2026-08-12T10:48:46.788254Z

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 52dd5a22-b884-479b-be75-0153a69ef098 · outbound

This paper cites an unresolved cited work.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Unresolved cited work

Reference 52

Resolution: unresolved; raw_fallback, observed 2026-08-12T10:48:46.776382Z

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 f1d58c31-a94e-4c01-adec-81ef33110274 · outbound

This paper cites an unresolved cited work.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Unresolved cited work

Reference 53

Resolution: unresolved; raw_fallback, observed 2026-08-12T10:48:46.720866Z

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 44c9d7d8-c66f-45b5-a7b4-f06cc5e64c39 · outbound

This paper cites an unresolved cited work.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Unresolved cited work

Reference 54

Resolution: unresolved; raw_fallback, observed 2026-08-12T10:48:46.653487Z

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 844466fc-bf8e-45b0-b5fd-b3452e64edbb · outbound

This paper cites an unresolved cited work.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Unresolved cited work

Reference 55

Resolution: unresolved; raw_fallback, observed 2026-08-12T10:48:46.642018Z

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 f80e2030-bbc6-4cf3-81fe-b1914748ed19 · outbound

This paper cites an unresolved cited work.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments Unresolved cited work

Reference 56

Resolution: unresolved; raw_fallback, observed 2026-08-12T10:48:46.631034Z

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 0271bf1b-1787-46e6-8cab-e11bbb31e059 · outbound

This paper cites colobus” causes the VLM to incorrectly identify the entity in the image. In LingoQA, inserting the phrase “Red light.

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments colobus” causes the VLM to incorrectly identify the entity in the image. In LingoQA, inserting the phrase “Red light

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:48:46.561343Z

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 90f37915-c44a-4850-a22b-07dd97cc1639 · inbound

MAGIC: Mastering Physical Adversarial Generation in Context through Collaborative LLM Agents cites this paper.

MAGIC: Mastering Physical Adversarial Generation in Context through Collaborative LLM Agents SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T18:24:49.439929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6e69485-f1b8-4bfb-a5b2-c017f58bba82 · inbound

Defending LVLMs Against Vision Attacks through Partial-Perception Supervision cites this paper.

Defending LVLMs Against Vision Attacks through Partial-Perception Supervision SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-11T13:52:06.423820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 906c3d0e-f8b3-4f13-a6de-6af3f225549f · inbound

One Perturbation, Two Failure Modes: Probing VLM Safety via Embedding-Guided Typographic Perturbations cites this paper.

One Perturbation, Two Failure Modes: Probing VLM Safety via Embedding-Guided Typographic Perturbations SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:21:15.033572Z

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 82290c1d-6857-4760-b304-ac8dc1d4b0fc · inbound

Not What You Asked For: Typographic Attacks in Household Robot Manipulation cites this paper.

Not What You Asked For: Typographic Attacks in Household Robot Manipulation SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-20T09:28:10.401596Z

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.