Paper Citation Record · LEDGER

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models

As of 18 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2510.17759.

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

pith.paper-citation-record.v1
2510.17759 v2

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T09:02:41.029778Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+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

37 of 37 outbound references displayed

verified exact0
verified fuzzy0
unresolved37
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 091f8ee0-ab77-4c76-aad0-fd5b72694fcc · outbound

This paper cites Qwen2.5-VL Technical Report.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Qwen2.5-VL Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:36.585841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6ff87cc-55f6-4fd3-83f7-8132cfddcc6e · outbound

This paper cites Trust-vlm: Thorough red-teaming for uncovering safety threats in vision-language models.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Trust-vlm: Thorough red-teaming for uncovering safety threats in vision-language models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:36.693293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 822e213c-bd6e-4428-a4fe-d57ff9776962 · outbound

This paper cites JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual Steering.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual Steering

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:36.800236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13326619-084b-42db-916e-3bb3d21b4adf · outbound

This paper cites Gonzalez, Ion Stoica, and Eric P.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Gonzalez, Ion Stoica, and Eric P

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:36.953149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8eaa35df-b236-42ce-a2d1-b764b1728477 · outbound

This paper cites Eta: Evaluating then aligning safety of vision language models at inference time.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Eta: Evaluating then aligning safety of vision language models at inference time

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:37.046720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6962335d-e8ab-44d5-97ea-00b444f5db40 · outbound

This paper cites Scaling rectified flow transformers for high-resolution image synthesis.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Scaling rectified flow transformers for high-resolution image synthesis

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:37.148757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d688941-46ad-4aaf-9f2d-088d0a311427 · outbound

This paper cites Figstep: Jailbreaking large vision-language models via typographic visual prompts.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Figstep: Jailbreaking large vision-language models via typographic visual prompts

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:37.370781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9adf6efa-39f9-4f04-a303-024b5adda4f7 · outbound

This paper cites The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:37.531373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 414a6897-861b-4f39-b9c4-a1ef332f6833 · outbound

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

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Lora: Low-rank adaptation of large language models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:37.657331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4b938b8-0588-4903-b0f2-26c079ca1d0a · outbound

This paper cites Images are achilles' heel of alignment: Exploiting visual vulnerabilities for jailbreaking multimodal large language models.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Images are achilles' heel of alignment: Exploiting visual vulnerabilities for jailbreaking multimodal large language models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:37.787749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c709635b-4625-4f7d-b9fa-534eb2b0a28c · outbound

This paper cites Images are achilles’ heel of alignment: Exploiting visual vulnerabilities for jailbreaking multimodal large language models.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Images are achilles’ heel of alignment: Exploiting visual vulnerabilities for jailbreaking multimodal large language models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:37.935623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf9bab15-904c-455e-bd2e-9bdf7b4e6b1f · outbound

This paper cites Vl-trojan: Multimodal instruction backdoor attacks against autoregressive visual language models.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Vl-trojan: Multimodal instruction backdoor attacks against autoregressive visual language models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:38.064964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72f10972-37fe-4be9-af0f-d6733e68f3ec · outbound

This paper cites Visual instruction tuning.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Visual instruction tuning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:38.117232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 257b9b0b-1e0d-493c-b832-35d95ca85419 · outbound

This paper cites Arondight: Red teaming large vision language models with auto-generated multi-modal jailbreak prompts.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Arondight: Red teaming large vision language models with auto-generated multi-modal jailbreak prompts

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:38.191281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81994794-73d5-4737-902b-fadf39160117 · outbound

This paper cites VERA: Variational Inference Framework for Jailbreaking Large Language Models.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models VERA: Variational Inference Framework for Jailbreaking Large Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:38.279815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c588d445-d65f-4da7-bfee-0f88f4afb94e · outbound

This paper cites Backdooring vision-language models with out-of-distribution data.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Backdooring vision-language models with out-of-distribution data

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:38.492727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59cd7582-ec3a-4e5a-9246-11362bc47eb0 · outbound

This paper cites Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:38.637172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47eb88d5-8b7d-4544-b473-3a07b91582a7 · outbound

This paper cites Forsyth, and Dan Hendrycks.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Forsyth, and Dan Hendrycks

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:38.813023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 497efb19-bc19-44ac-8cc9-4ceb95cea2f9 · outbound

This paper cites Jailbreaking Attack against Multimodal Large Language Model.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Jailbreaking Attack against Multimodal Large Language Model

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:38.962519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4649dad8-2c8f-4f16-9969-4600e5505cf2 · outbound

This paper cites Hello gpt-4o, 2024 a.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Hello gpt-4o, 2024 a

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:39.128534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da2bd73e-ae9c-44d6-a656-f1326093b6b4 · outbound

This paper cites Gpt-4o mini: Advancing cost-efficient intelligence, 2024 b.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Gpt-4o mini: Advancing cost-efficient intelligence, 2024 b

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:39.254091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dadd5531-ff1d-44e6-aedc-3ccc2cf2827b · outbound

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

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Learning To See But Forgetting To Follow: Visual Instruction Tuning Makes LLMs More Prone To Jailbreak Attacks

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:39.371506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44df4ca0-2727-458e-80f4-516314822216 · outbound

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

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Visual adversarial examples jailbreak aligned large language models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:39.498249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae799f24-33b2-466b-b074-5fb104fdb242 · outbound

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

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Vision-LLMs Can Fool Themselves with Self-Generated Typographic Attacks

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:39.623038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2549ffbb-e9e0-43bd-af0f-37b5366acbe2 · outbound

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

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Jailbreak in pieces: Compositional adversarial attacks on multi-modal language models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:39.794461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ec290b4-3d51-490c-9ec3-ad4fe12b499a · outbound

This paper cites A strongreject for empty jailbreaks.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models A strongreject for empty jailbreaks

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:39.855246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5aa58fde-4c0b-4fa3-9308-6ec03bda1952 · outbound

This paper cites Imgtrojan: Jailbreaking vision-language models with ONE image.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Imgtrojan: Jailbreaking vision-language models with ONE image

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:39.941181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c02fb54-f84d-4526-8ab4-26af9073ccc9 · outbound

This paper cites Ideator: Jailbreaking and benchmarking large vision-language models using themselves.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Ideator: Jailbreaking and benchmarking large vision-language models using themselves

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:40.051324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e210163-3f8a-407e-8757-f27ce44d7a38 · outbound

This paper cites Jailbreak large vision-language models through multi-modal linkage.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Jailbreak large vision-language models through multi-modal linkage

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:40.152235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52927ac3-116f-4a00-bce0-c5ab5b265af2 · outbound

This paper cites Simple statistical gradient-following algorithms for connectionist reinforcement learning.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Simple statistical gradient-following algorithms for connectionist reinforcement learning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:40.234142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91f7918b-66f7-4817-ab8c-7c893431ab87 · outbound

This paper cites Distraction is all you need for multimodal large language model jailbreaking.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Distraction is all you need for multimodal large language model jailbreaking

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:40.324350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation daee661d-3b7b-47f8-a12d-ecb072bc89bb · outbound

This paper cites Anyattack: Towards large-scale self-supervised adversarial attacks on vision-language models.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Anyattack: Towards large-scale self-supervised adversarial attacks on vision-language models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:40.441757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74d883df-13ad-462b-9443-1746eb1de9d7 · outbound

This paper cites InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:40.543643Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 573a73fc-0bb4-4d46-a44b-f90e820b36ac · outbound

This paper cites write newline.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models write newline

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:40.666405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2d0ce8c-4fe0-4f23-8812-cf1c2369cf0a · outbound

This paper cites @esa (Ref.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models @esa (Ref

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:40.833370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 399611c8-40de-44ec-86f1-68bd2449fc8c · outbound

This paper cites an unresolved cited work.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Unresolved cited work

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:40.913886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 488101bd-a5ae-4d55-91c9-568c30c5f659 · outbound

This paper cites an unresolved cited work.

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Unresolved cited work

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T09:02:41.029778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.