Paper Citation Record · LEDGER

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models

As of 7 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 0 inbound Pith citation observations for arXiv:2507.08982.

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

pith.paper-citation-record.v1
2507.08982 v1

Coverage vector

measured 48 of 48 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T18:16:31.806132Z

measured 48 of 48 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+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

48 of 48 outbound references displayed

verified exact2
verified fuzzy15
unresolved30
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 27319ba2-0a68-4d01-ba80-77cd213fd58e · outbound

This paper cites GPT-4 Technical Report.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:28.313408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6319c400-7eb6-45af-b32d-67e090d954e1 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Gemini: A Family of Highly Capable Multimodal Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:28.361118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96a6b29a-9892-4e5a-b7d8-4c5396a76d2e · outbound

This paper cites Pixtral 12B.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Pixtral 12B

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:28.456642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3e25417-5864-4888-a920-35b88ceee824 · outbound

This paper cites Aria: An Open Multimodal Native Mixture-of-Experts Model.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Aria: An Open Multimodal Native Mixture-of-Experts Model

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:28.576320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc2bae78-e581-48f4-8cdb-a3a4d930f6d7 · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:28.671502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55971cd9-f361-4ae7-84ec-6d667772de97 · outbound

This paper cites Reconstructing training data from diverse ml models by ensemble inversion,.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Reconstructing training data from diverse ml models by ensemble inversion,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:16:35.106727Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f61a5fc9-425c-45cc-8aee-853770267d31 · outbound

This paper cites Effective prompt extraction from language models,.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Effective prompt extraction from language models,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:16:34.942391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c7f0254b-699d-476d-ae2f-871e22513447 · outbound

This paper cites Extracting training data from large language models,.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Extracting training data from large language models,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:28.886540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77670c13-7295-4ad5-87db-706dc8d232c5 · outbound

This paper cites Are aligned neural networks adversarially aligned?.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Are aligned neural networks adversarially aligned?

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:16:34.824986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1f7b0e40-1b50-437e-8cd2-211aa344c194 · outbound

This paper cites Jailbreak in pieces: Compositional adversarial attacks on multi-modal language models,.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Jailbreak in pieces: Compositional adversarial attacks on multi-modal language models,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:16:34.588236Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a9517a8d-3314-4080-958f-1a3a7effefec · outbound

This paper cites On the robustness of large multimodal models against image adversarial attacks,.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models On the robustness of large multimodal models against image adversarial attacks,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:16:34.438093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 50fb1c4f-19d8-4e2e-9546-f2a1fe5d90f3 · outbound

This paper cites An image is worth 1000 lies: Transferability of adversarial images across prompts on vision-language models,.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models An image is worth 1000 lies: Transferability of adversarial images across prompts on vision-language models,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:16:34.287767Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 462880f4-3997-471c-bb04-1ce23bc6d017 · outbound

This paper cites As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks?.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks?

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:29.252024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bb7b1a7-1c01-4795-be3e-b3138c13b568 · outbound

This paper cites Inducing high energy-latency of large vision-language models with verbose images,.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Inducing high energy-latency of large vision-language models with verbose images,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:16:34.028772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 072575c3-4d01-4208-b890-995a4f8d6de2 · outbound

This paper cites Tafim: Targeted adversarial attacks against facial image manipulations,.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Tafim: Targeted adversarial attacks against facial image manipulations,

Reference 15

Resolution: malformed identifier; raw_fallback, observed 2026-08-06T18:16:33.865713Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f3aeb4aa-6c06-43eb-b6cf-35e6bb2a8e0b · outbound

This paper cites Adversary for social good: Leveraging adversarial attacks to protect personal attribute privacy,.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Adversary for social good: Leveraging adversarial attacks to protect personal attribute privacy,

Reference 16

Resolution: verified exact; doi, observed 2026-08-06T18:16:31.958086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c26c49ee-07bd-446b-9729-c1ceebb6150b · outbound

This paper cites M$^3$IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models M$^3$IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:29.523026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7cb831e-7465-437f-b74a-76bbaf1944ff · outbound

This paper cites InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:29.579029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c299d28a-fd1a-4a15-a0af-c4492c474355 · outbound

This paper cites Blip-2: Bootstrapping language- image pre-training with frozen image encoders and large language models,.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Blip-2: Bootstrapping language- image pre-training with frozen image encoders and large language models,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:29.654419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4667c84a-d20b-4ce5-9d97-70a7715ffa1d · outbound

This paper cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:29.743840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5f28faf-7cbe-46be-9b07-d17b2140f5af · outbound

This paper cites Language models are unsupervised multitask learners,.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Language models are unsupervised multitask learners,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:29.803032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 614d5c50-ce62-4adb-97b8-bee3e6172aee · outbound

This paper cites Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality,.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:29.899551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a9d4257-814e-493d-b8d0-0f53a8cf49d2 · outbound

This paper cites Eva: Exploring the limits of masked visual representation learning at scale,.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Eva: Exploring the limits of masked visual representation learning at scale,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:16:33.746434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 76ffd6b0-6ace-4319-ac56-16600f5ec538 · outbound

This paper cites Scaling instruction-finetuned language models,.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Scaling instruction-finetuned language models,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:30.031158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52696ab0-b564-4103-90bb-5906b1637637 · outbound

This paper cites DeepSeek-V3 Technical Report.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models DeepSeek-V3 Technical Report

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:30.081693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8170ba0-2e2b-4ad5-92b7-e7c490d77d28 · outbound

This paper cites The Llama 3 Herd of Models.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models The Llama 3 Herd of Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:30.177401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9d18ef2-6c16-4bb9-a918-b09ee3360529 · outbound

This paper cites Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:30.236877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48b84086-6767-4331-8b06-578b6a32aa09 · outbound

This paper cites NVLM: Open Frontier-Class Multimodal LLMs.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models NVLM: Open Frontier-Class Multimodal LLMs

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:30.308560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b61e8ae3-9bd5-4b4e-9b41-365bd10a469a · outbound

This paper cites MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:30.360814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3cb9009-7e9f-4463-b75e-f9a13a447a0f · outbound

This paper cites Emu3: Next-Token Prediction is All You Need.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Emu3: Next-Token Prediction is All You Need

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:30.444420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a64832e3-2ba0-4181-b03a-1ac47b88a05f · outbound

This paper cites Intriguing properties of neural networks.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Intriguing properties of neural networks

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:30.491722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b8b206d-695f-40c2-aef4-f1dd83b5538e · outbound

This paper cites Deep neural networks are easily fooled: High confidence predictions for unrecognizable images,.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Deep neural networks are easily fooled: High confidence predictions for unrecognizable images,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:16:33.436473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 50e77a7e-42ac-4e05-a533-121fb7ca451c · outbound

This paper cites Explaining and Harnessing Adversarial Examples.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Explaining and Harnessing Adversarial Examples

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:30.690815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f790c834-5587-4aca-958b-ef57e24a3804 · outbound

This paper cites A limited memory algo- rithm for bound constrained optimization,.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models A limited memory algo- rithm for bound constrained optimization,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:30.745723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4db6ec5-e216-4378-8587-e7c7e974a15e · outbound

This paper cites Towards evaluating the robustness of neural networks,.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Towards evaluating the robustness of neural networks,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:30.822007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0692a410-89e6-4a48-ae58-ce70ce9e6c1f · outbound

This paper cites Zoo: Zeroth order optimization based black-box attacks to deep neural networks without training substitute models,.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Zoo: Zeroth order optimization based black-box attacks to deep neural networks without training substitute models,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:16:33.266545Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 14078f29-cd0b-4a19-9ff0-77c86202e993 · outbound

This paper cites Towards deep learning models resistant to adversarial attacks,.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Towards deep learning models resistant to adversarial attacks,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:16:33.091742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 84348b1e-8475-4e9c-ba86-3ddb08e1b3cf · outbound

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

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:16:33.016948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a212794e-1309-4fca-88e9-9af6303c0159 · outbound

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

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models On evaluating adversarial robustness of large vision-language models,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:16:32.827988Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3db2ed7e-2742-4026-8957-8f8ee761eb7e · outbound

This paper cites Attacking attention of foundation models disrupts downstream tasks,.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Attacking attention of foundation models disrupts downstream tasks,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:16:32.629518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 855a97b9-aaa8-4061-894a-dcb1915dafd6 · outbound

This paper cites QAVA: Query-Agnostic Visual Attack to Large Vision-Language Models.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models QAVA: Query-Agnostic Visual Attack to Large Vision-Language Models

Reference 41

Resolution: verified exact; local_arxiv, observed 2026-08-06T18:16:32.129974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1f56de79-03f2-485f-8b22-1c4a4159ae84 · outbound

This paper cites Attention is all you need,.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Attention is all you need,

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:31.361308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 421f392e-0dab-4877-91ac-5038169a3b41 · outbound

This paper cites Imagenet large scale visual recognition challenge,.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Imagenet large scale visual recognition challenge,

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:31.419667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd91ff20-91cc-438f-8ee9-99a8b772a70c · outbound

This paper cites Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:31.481468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 523e00f6-5b53-4253-85e5-06156e3178ca · outbound

This paper cites Universal Sentence Encoder.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Universal Sentence Encoder

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:31.547114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fce1d07d-6175-43a1-bc44-a9b1a2b1e587 · outbound

This paper cites Mpnet: Masked and permuted pre-training for language understanding,.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Mpnet: Masked and permuted pre-training for language understanding,

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:16:32.465736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation dd0ca6f7-83e7-4b4c-9565-791e73502c3c · outbound

This paper cites Adam: A Method for Stochastic Optimization.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Adam: A Method for Stochastic Optimization

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:31.703850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c726c330-bfe5-4691-807a-92c4078ef2cf · outbound

This paper cites Quantifying Attention Flow in Transformers.

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models Quantifying Attention Flow in Transformers

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-06T18:16:31.806132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.