Paper Citation Record · LEDGER

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness

As of 18 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 3 inbound Pith citation observations for arXiv:2501.09446.

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

pith.paper-citation-record.v1
2501.09446 v2

Coverage vector

measured 58 of 58 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T20:06:24.676479Z

measured 61 of 61 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T02:57:46.941141Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T02:16:26.845312Z

Reference resolution

58 of 58 outbound references displayed

verified exact0
verified fuzzy40
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4e1776f9-a3f9-45c4-8a19-f3093e62184f · outbound

This paper cites Vqa: Visual question answering.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Vqa: Visual question answering

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:25.091010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1953bcb1-fd59-4b1f-8313-22cd0a0cdf91 · outbound

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

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Obfus- cated gradients give a false sense of security: Circumventing defenses to adversarial examples

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:25.084288Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 707a7573-b362-4d61-8b22-3a887b380ca3 · outbound

This paper cites Image hijacking: Adversarial images can control generative models at runtime.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Image hijacking: Adversarial images can control generative models at runtime

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:25.077462Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ce72e92f-bf34-4f07-8a9f-df8aa1fdf273 · outbound

This paper cites Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-10T20:06:24.514368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05fa27be-7460-4582-8546-3e277b3515bf · outbound

This paper cites Jax: composable transformations of python+ numpy programs.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Jax: composable transformations of python+ numpy programs

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:25.069948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a96207da-6122-4dbe-896b-83229788ba33 · outbound

This paper cites Towards evaluating the robustness of neural networks.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Towards evaluating the robustness of neural networks

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:25.062423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2cbaa20a-ad8f-4af7-b0b4-87e6a423bef5 · outbound

This paper cites Are aligned neural networks adversarially aligned? Advances in Neural Information Processing Systems, 36, 2024.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Are aligned neural networks adversarially aligned? Advances in Neural Information Processing Systems, 36, 2024

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:25.055620Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 48b260d2-c1f2-4246-86e5-5068391c03e4 · outbound

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

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Reliable evalua- tion of adversarial robustness with an ensemble of diverse parameter-free attacks

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:25.047481Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e93064c1-2041-4a2d-aeb2-4354a36c88ad · outbound

This paper cites InstructBLIP: Towards general-purpose vision-language models with instruction tuning.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness InstructBLIP: Towards general-purpose vision-language models with instruction tuning

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:25.040227Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0850d889-3fce-4a80-800b-8db8ec7accf4 · outbound

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

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Robust physical-world attacks on deep learning visual classification

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:25.033084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 757c5b33-d177-4def-8f28-88b475a703ad · outbound

This paper cites MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T20:06:24.534593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da759870-ac22-4f77-8e9f-c620861829d1 · outbound

This paper cites Dat- acomp: In search of the next generation of multimodal datasets.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Dat- acomp: In search of the next generation of multimodal datasets

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:25.025313Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 68faee73-b6c2-4a4d-be86-451e438c806a · outbound

This paper cites FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T20:06:24.539812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 788f875e-b592-407a-a22f-0735ed5c26e1 · outbound

This paper cites Explaining and harnessing adversarial examples.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Explaining and harnessing adversarial examples

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:25.016699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ee209832-6359-4738-afb7-b08e83a87b18 · outbound

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

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Making the v in vqa matter: Elevating the role of image understanding in visual question answer- ing

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:25.009177Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f706e098-4935-48f5-aaf6-3466c55ca202 · outbound

This paper cites Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-10T20:06:24.548987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d052b8ce-af60-4f6e-a058-3dda08431dad · outbound

This paper cites Vizwiz grand challenge: Answering visual questions from blind people.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Vizwiz grand challenge: Answering visual questions from blind people

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T20:06:24.552414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f472f45-7593-4d83-ae68-a92d9f8a03cc · outbound

This paper cites LoRA: Low-rank adaptation of large language models.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness LoRA: Low-rank adaptation of large language models

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:24.998152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c4971c88-7bc8-4620-a63f-35387a0a2163 · outbound

This paper cites Gqa: A new dataset for real-world visual reasoning and compositional question answering.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Gqa: A new dataset for real-world visual reasoning and compositional question answering

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:24.989646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 55d586a0-9a53-4bff-bf59-45f2111d4027 · outbound

This paper cites Collecting a large-scale dataset of fine-grained cars.(2013).

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Collecting a large-scale dataset of fine-grained cars.(2013)

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:24.982411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b7ccd5bd-2c60-4193-b74e-29a7c531c02b · outbound

This paper cites What If We Recaption Billions of Web Images with LLaMA-3?.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness What If We Recaption Billions of Web Images with LLaMA-3?

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-10T20:06:24.564806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73bd220d-a2ae-4084-a384-1a02dfbb3eb9 · outbound

This paper cites An inverse scal- ing law for clip training.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness An inverse scal- ing law for clip training

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:24.974131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation eea723d3-132a-4530-b8ae-21d10ba7601e · outbound

This paper cites Evaluating object hallucination in large vision-language models.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Evaluating object hallucination in large vision-language models

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:24.966911Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0e166030-19d9-4a5c-b291-3aa1e18bcf1d · outbound

This paper cites Scaling language-image pre-training via masking.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Scaling language-image pre-training via masking

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:24.959996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7dce995a-6755-49a4-b97c-b111622e3521 · outbound

This paper cites Microsoft coco: Common objects in context.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Microsoft coco: Common objects in context

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-10T20:06:24.576699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 248c01ea-a96a-49b3-995d-e45a0ae1282e · outbound

This paper cites Improved baselines with visual instruction tuning.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Improved baselines with visual instruction tuning

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:24.949057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ef4277ab-62ff-4b1a-b74b-6eef7ce7000a · outbound

This paper cites Visual instruction tuning.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Visual instruction tuning

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:24.941936Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5d57b010-6409-4b93-9338-ac143c8aa848 · outbound

This paper cites AutoDAN: Generating stealthy jailbreak prompts on aligned large language models.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness AutoDAN: Generating stealthy jailbreak prompts on aligned large language models

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:24.933651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 213a7dd0-0c0c-403a-981f-87062b9f6291 · outbound

This paper cites Learn to explain: Multimodal reasoning via thought chains for science question answering.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Learn to explain: Multimodal reasoning via thought chains for science question answering

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-10T20:06:24.586907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94369438-5983-40ff-826c-3163b35467b8 · outbound

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

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Towards deep learning models resistant to adversarial attacks

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:24.922818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5944b3f7-8e89-4ca7-b0c4-327b9ca5cce5 · outbound

This paper cites Understanding zero-shot adversarial robust- ness for large-scale models.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Understanding zero-shot adversarial robust- ness for large-scale models

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:24.915549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d556e3a8-f0d7-439f-a070-0d34b539c37a · outbound

This paper cites Deepfool: a simple and accurate method to fool deep neural networks.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Deepfool: a simple and accurate method to fool deep neural networks

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-10T20:06:24.595517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdf56dc0-8e55-4392-8ed8-56becba3d80a · outbound

This paper cites Bag of tricks for adversarial training.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Bag of tricks for adversarial training

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:24.904859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f12e9d07-da67-49af-9d46-e5fc31267973 · outbound

This paper cites Learning To See But Forgetting To Follow: Visual Instruction Tuning Makes LLMs More Prone To Jailbreak Attacks.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Learning To See But Forgetting To Follow: Visual Instruction Tuning Makes LLMs More Prone To Jailbreak Attacks

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-10T20:06:24.601160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbc0083e-1950-48ec-869b-95fdb093f31f · outbound

This paper cites Flickr30k entities: Collecting region-to-phrase corre- spondences for richer image-to-sentence models.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Flickr30k entities: Collecting region-to-phrase corre- spondences for richer image-to-sentence models

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:24.897410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 29cce8ce-5de9-4ca8-8843-04b3bd982534 · outbound

This paper cites Visual Adversarial Examples Jailbreak Aligned Large Language Models.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Visual Adversarial Examples Jailbreak Aligned Large Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-10T20:06:24.607796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcc9fe5d-90ee-4e2d-95bc-428aa1ce8f2c · outbound

This paper cites Visual adversarial examples jailbreak aligned large language models.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Visual adversarial examples jailbreak aligned large language models

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:24.890475Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6b7bd383-f61b-4a93-879d-b3fda75be958 · outbound

This paper cites Fine-tuning aligned language models compromises safety, even when users do not intend to! In The Twelfth International Conference on Learning Representations, 2024.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Fine-tuning aligned language models compromises safety, even when users do not intend to! In The Twelfth International Conference on Learning Representations, 2024

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:24.883310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 26aeb469-7347-48ec-9aee-c7d26101fb77 · outbound

This paper cites Learn- ing transferable visual models from natural language super- vision.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Learn- ing transferable visual models from natural language super- vision

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:24.875761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 82a9f85a-2e5b-4e8a-a2f7-5997a119c15c · outbound

This paper cites Failures to Find Transferable Image Jailbreaks Between Vision-Language Models.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Failures to Find Transferable Image Jailbreaks Between Vision-Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-10T20:06:24.619802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c0b25ae-eb55-48ca-905e-2a9518b4b3e2 · outbound

This paper cites on the adversar- ial robustness of multi-modal foundation models.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness on the adversar- ial robustness of multi-modal foundation models

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:24.867179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 07f5391d-2958-48de-be57-a17e25675266 · outbound

This paper cites Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-10T20:06:24.626038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ece5ae28-d52b-4aab-b852-f61b17148b5e · outbound

This paper cites Adversarial training for free! NeurIPS, 32, 2019.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Adversarial training for free! NeurIPS, 32, 2019

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:24.858541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 72eee1f7-2fd3-4259-b926-a77f6e53ff14 · outbound

This paper cites Towards vqa models that can read.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Towards vqa models that can read

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:24.850576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1b70138a-de70-458b-9c42-0742c26f3845 · outbound

This paper cites EVA-CLIP: Improved Training Techniques for CLIP at Scale.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness EVA-CLIP: Improved Training Techniques for CLIP at Scale

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-10T20:06:24.636036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d0c19ab-51f6-4a05-b6e2-23655501e6b0 · outbound

This paper cites In- triguing properties of neural networks.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness In- triguing properties of neural networks

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:24.843355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 51cfb025-1c29-4539-8f49-511e486369b2 · outbound

This paper cites Robustness May Be at Odds with Accuracy.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Robustness May Be at Odds with Accuracy

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-10T20:06:24.641502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e56ae7a6-cc41-4e8d-ae8c-a165d86614a5 · outbound

This paper cites Cider: Consensus-based image description evalua- tion.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Cider: Consensus-based image description evalua- tion

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-10T20:06:24.644618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53a731f3-6e49-4c44-9fc6-2f7dcd64e6c4 · outbound

This paper cites Revisiting adversarial training at scale.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Revisiting adversarial training at scale

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:24.831539Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6db1a99e-93fb-4d9f-a784-2ea8cbbe4510 · outbound

This paper cites Zico Kolter.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Zico Kolter

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:24.823804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 57a563a4-ff85-4f1e-bad9-216cae047c51 · outbound

This paper cites On the safety concerns of deploying 14 llms/vlms in robotics: Highlighting the risks and vulnerabil- ities.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness On the safety concerns of deploying 14 llms/vlms in robotics: Highlighting the risks and vulnerabil- ities

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:24.815350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c6283cf5-d438-48d9-aee3-b1a49af7f99f · outbound

This paper cites Feature denoising for improving ad- versarial robustness.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Feature denoising for improving ad- versarial robustness

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:24.806475Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 16f13be1-37b3-4f63-a5f0-faf8bdbfc405 · outbound

This paper cites Coca: Contrastive captioners are image-text foundation models.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Coca: Contrastive captioners are image-text foundation models

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:24.796927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 732067d3-7c24-4928-b2c3-dbf6bdb75365 · outbound

This paper cites Towards robust resnet: A small step but a giant leap.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Towards robust resnet: A small step but a giant leap

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:24.789140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d4e81124-00cf-49c2-bff3-08dbdddc8ecc · outbound

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

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Attacks which do not kill training make adversarial learning stronger

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:24.781588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ec52100a-d665-4119-83df-c3dd69b5c902 · outbound

This paper cites Geometry-aware instance-reweighted adversarial training.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Geometry-aware instance-reweighted adversarial training

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:06:24.773519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 22610ae9-0f3f-4e3e-bb3d-a7a28ae35c7f · outbound

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

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-10T20:06:24.673382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a0fbdf1-167c-4dfc-8fe4-5e62dee3e157 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-10T20:06:24.676479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation b813acf5-d0c6-4524-b03a-fbfe460883b9 · inbound

Grounding-Driven Attack: Improving Encoder-based Adversarial Transferability against Large Vision-Language Models cites this paper.

Grounding-Driven Attack: Improving Encoder-based Adversarial Transferability against Large Vision-Language Models Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-03T02:57:46.941141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ad91002-c2e8-4cf7-879f-29230efe9357 · inbound

Investigating Adversarial Robustness of Multi-modal Large Language Models cites this paper.

Investigating Adversarial Robustness of Multi-modal Large Language Models Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness

Reference 62

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:06:27.573666Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0372334e-33ec-463c-9677-8bba24ef033d · inbound

Beyond False Stability: High-Noise Drift Gating for Test-Time Adversarial Defenses in Vision-Language Models cites this paper.

Beyond False Stability: High-Noise Drift Gating for Test-Time Adversarial Defenses in Vision-Language Models Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:16:26.847659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.