Paper Citation Record · LEDGER

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models

As of 10 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 0 inbound Pith citation observations for arXiv:2604.16499.

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

pith.paper-citation-record.v1
2604.16499 v1

Coverage vector

measured 40 of 40 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T16:23:13.730247Z

measured 40 of 40 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

40 of 40 outbound references displayed

verified exact2
verified fuzzy35
unresolved2
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8c6f84a5-84a8-46b0-a235-0b4bdab82e16 · outbound

This paper cites Image captioning with novel topics guidance and retrieval-based topics re-weighting.IEEE Transactions on Multimedia (TMM), 25:5984–5999.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Image captioning with novel topics guidance and retrieval-based topics re-weighting.IEEE Transactions on Multimedia (TMM), 25:5984–5999

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.195817Z

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 784eb8f1-1d72-46c8-bdb4-f34aecc0cf66 · outbound

This paper cites SPICE: semantic propositional image caption evaluation.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models SPICE: semantic propositional image caption evaluation

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.159462Z

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 71bd2170-bff8-49c5-89fe-46f78d46830a · outbound

This paper cites METEOR: an automatic metric for MT evaluation with improved correlation with human judgments.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models METEOR: an automatic metric for MT evaluation with improved correlation with human judgments

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.186653Z

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 7097ea62-30ee-40f5-a7a2-62aa3e1d6af8 · outbound

This paper cites Image-text retrieval: A survey on recent research and development.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Image-text retrieval: A survey on recent research and development

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.166533Z

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 a679c783-7d4d-46be-abb8-aedf373f53c4 · outbound

This paper cites Query-efficient decision-based black-box patch attack.IEEE Transactions on Information Forensics and Security, 18:5522–5536.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Query-efficient decision-based black-box patch attack.IEEE Transactions on Information Forensics and Security, 18:5522–5536

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.181531Z

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 7ea89b6e-9c41-4ecb-931b-dd8b7a1f251b · outbound

This paper cites Transfer Attack for Bad and Good: Explain and Boost Adversarial Transferability across Multimodal Large Language Models.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Transfer Attack for Bad and Good: Explain and Boost Adversarial Transferability across Multimodal Large Language Models

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-11T08:56:03.256500Z

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 fcc84b80-7820-44c2-9750-45cd8a0effe6 · outbound

This paper cites Cross-modal alignment with graph reasoning for image-text retrieval.Multimedia Tools and Applications, 81(17):23615–23632.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Cross-modal alignment with graph reasoning for image-text retrieval.Multimedia Tools and Applications, 81(17):23615–23632

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.193063Z

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 246cb788-110f-4e8a-9035-f3eda1ef8022 · outbound

This paper cites BERT: pre-training of deep bidirectional transformers for language understanding.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models BERT: pre-training of deep bidirectional transformers for language understanding

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.201428Z

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 30878d32-a314-48ae-8684-a11b697035a8 · outbound

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

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models An image is worth 16x16 words: Transformers for image recognition at scale

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.155733Z

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 3eb3d9a8-ab3e-47f4-b885-84e86f7d2110 · outbound

This paper cites Tsang, and Qing Guo.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Tsang, and Qing Guo

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.204417Z

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 601632cf-57e3-4cd6-9fc6-796d146ca731 · outbound

This paper cites Adversarial neural collaborative filtering with embedding dimension correlations.Data Intelligence, 5(3):786–806.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Adversarial neural collaborative filtering with embedding dimension correlations.Data Intelligence, 5(3):786–806

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.207236Z

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 8ce35eb7-f5ff-40a8-9091-9909f3431d73 · outbound

This paper cites Deep residual learning for image recognition.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Deep residual learning for image recognition

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.151652Z

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 913dae38-cfe5-4f58-930d-aff0a6e706ff · outbound

This paper cites Selvaraju, Akhilesh Gotmare, Shafiq R.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Selvaraju, Akhilesh Gotmare, Shafiq R

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.276692Z

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 ab3525f5-27ef-4237-ae4a-fb4e1a443a8e · outbound

This paper cites BERT-ATTACK: adversarial attack against BERT using BERT.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models BERT-ATTACK: adversarial attack against BERT using BERT

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.189812Z

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 7e629167-ce92-4960-8f88-d8a3e4cffd10 · outbound

This paper cites Rouge: A package for automatic evaluation of summaries.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Rouge: A package for automatic evaluation of summaries

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.225911Z

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 f9d80d22-9495-4bed-916b-501fda11a69a · outbound

This paper cites Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.177727Z

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 a007ae65-fb50-437b-8ad7-c1308dca825f · outbound

This paper cites Sspattack: A simple and sweet paradigm for black-box hard-label textual adversarial attack.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Sspattack: A simple and sweet paradigm for black-box hard-label textual adversarial attack

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.243922Z

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 f0a3181a-c493-4a30-92a3-620b1f5801af · outbound

This paper cites Hqa-attack: Toward high quality black-box hard-label adversarial attack on text.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Hqa-attack: Toward high quality black-box hard-label adversarial attack on text

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.144112Z

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 abbd5615-8b8e-4ea0-9e2a-79ca81cefed4 · outbound

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

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Set-level guidance attack: Boosting adversarial transferability of vision-language pre-training models

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.147971Z

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 dae1e8cd-7e61-4045-af85-4d07b5491a6a · outbound

This paper cites Groma: Localized visual tokenization for grounding multimodal large language models.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Groma: Localized visual tokenization for grounding multimodal large language models

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.140605Z

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 92f1c702-e448-4d3b-9b57-534050b803a0 · outbound

This paper cites To- wards deep learning models resistant to adversarial attacks.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models To- wards deep learning models resistant to adversarial attacks

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.222425Z

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 7bf0bd3d-8a38-478c-b65d-eed6e3cb4967 · outbound

This paper cites an unresolved cited work.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-05-17T15:39:54.136566Z

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 9736906d-1960-441c-8c16-e47c8ef5bffb · outbound

This paper cites GPT-4 Technical Report.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models GPT-4 Technical Report

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-11T08:56:03.263191Z

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 d17e091c-001c-47ee-b561-da14279fe799 · outbound

This paper cites Bleu: a method for automatic evaluation of machine translation.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Bleu: a method for automatic evaluation of machine translation

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.210181Z

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 70823cc6-109a-488b-b644-a673bc6ed547 · outbound

This paper cites Plummer, Liwei Wang, Chris M.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Plummer, Liwei Wang, Chris M

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.128736Z

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 1e81c976-6ede-4d20-83a6-36b184b8dcbe · outbound

This paper cites Learning transferable visual models from natural language supervision.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Learning transferable visual models from natural language supervision

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.133408Z

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 7ebd3c3f-abe2-4943-804c-0818474a38bd · outbound

This paper cites From show to tell: A survey on deep learning-based image captioning.IEEE Trans.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models From show to tell: A survey on deep learning-based image captioning.IEEE Trans

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.240289Z

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 a319177b-cea7-4d7f-9ed8-34ef8866a077 · outbound

This paper cites Lawrence Zitnick, and Devi Parikh.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Lawrence Zitnick, and Devi Parikh

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.198519Z

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 6ac3cafb-e1b0-45f9-b06b-47e35b36e3df · outbound

This paper cites A text-guided generation and refinement model for image captioning.IEEE Transactions on Multimedia (TMM), 25:2966–2977.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models A text-guided generation and refinement model for image captioning.IEEE Transactions on Multimedia (TMM), 25:2966–2977

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.170669Z

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 3d94bd66-0f1c-47a9-b6a9-876bc094d5d4 · outbound

This paper cites Fine-grained image captioning with global-local discriminative objective.IEEE Transactions on Multimedia (TMM), 23:2413– 2427.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Fine-grained image captioning with global-local discriminative objective.IEEE Transactions on Multimedia (TMM), 23:2413– 2427

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.174331Z

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 8bf95c04-e51a-40bb-b445-0bc6271d7774 · outbound

This paper cites an unresolved cited work.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-05-17T15:39:54.273202Z

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 a9e3fb60-c71c-4966-b21d-a80692e5ca6b · outbound

This paper cites Fooling vision and language models despite localization and attention mechanism.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Fooling vision and language models despite localization and attention mechanism

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.261255Z

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 12471d53-5070-4641-99e7-bea6be92944d · outbound

This paper cites Vision-language pre-training with triple contrastive learning.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Vision-language pre-training with triple contrastive learning

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.267594Z

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 f3c0c5d7-cb8a-4577-bc6e-c104302231e5 · outbound

This paper cites VLATTACK: multimodal adversarial attacks on vision-language tasks via pre-trained models.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models VLATTACK: multimodal adversarial attacks on vision-language tasks via pre-trained models

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.264434Z

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 6aa4a777-2578-41f6-bc3d-54bdc062dcc6 · outbound

This paper cites Vqattack: Transferable adversarial attacks on visual question answering via pre-trained models.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Vqattack: Transferable adversarial attacks on visual question answering via pre-trained models

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.251414Z

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 a437e208-3cb7-46cd-b586-2a2256604ef7 · outbound

This paper cites Berg, and Tamara L.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Berg, and Tamara L

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.258333Z

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 585f7f51-9e45-4d00-bda0-d4589a056079 · outbound

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

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Towards adversarial attack on vision-language pre-training models

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.163199Z

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 a37d03ac-236b-49bc-ae8c-e7beffa3c92f · outbound

This paper cites Universal adversarial perturbations for vision-language pre-trained models.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Universal adversarial perturbations for vision-language pre-trained models

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.247761Z

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 cabc2bc9-1df8-4534-acae-65499310f670 · outbound

This paper cites Limitations.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Limitations

Reference 39

Resolution: malformed identifier; raw_fallback, observed 2026-05-17T15:39:54.270585Z

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 643e9994-5e7b-4059-a8ba-d436eaed617c · outbound

This paper cites Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects.

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:39:54.255177Z

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.