Paper Citation Record · LEDGER

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities

As of 9 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 1 inbound Pith citation observation for arXiv:2506.00548.

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

pith.paper-citation-record.v1
2506.00548 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:08:01.411183Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-20T14:46:52.070071Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-20T14:48:23.261637Z

Reference resolution

37 of 37 outbound references displayed

verified exact2
verified fuzzy0
unresolved35
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 668fd8a5-7bb3-48dd-a48e-732dfcab98fc · outbound

This paper cites GPT-4 Technical Report.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:57.985841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e45d494d-1e18-483f-80c2-3892c392dc02 · outbound

This paper cites Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:58.079163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 918d8786-856c-44f0-9877-fc448dccb352 · outbound

This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:58.191086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b5915c6-681e-41a8-81d0-73865e04c1f5 · outbound

This paper cites Image Hijacks: Adversarial Images can Control Generative Models at Runtime.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities Image Hijacks: Adversarial Images can Control Generative Models at Runtime

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:58.302229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf9db7b5-2b2b-4349-92dc-c682e659f22d · outbound

This paper cites an unresolved cited work.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:08:04.167676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bcbdb15b-d5d1-4d4e-b65c-d5f42b7c1478 · outbound

This paper cites an unresolved cited work.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:58.505183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0b44c36-2a93-4f62-8371-844350562b12 · outbound

This paper cites Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:58.606775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5086852-280e-487f-be1b-9cfb95f22b1e · outbound

This paper cites How Robust is Google's Bard to Adversarial Image Attacks?.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities How Robust is Google's Bard to Adversarial Image Attacks?

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:58.704370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5b44c31-34e4-44be-a78c-dfcda1868867 · outbound

This paper cites an unresolved cited work.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities Unresolved cited work

Reference 9

Resolution: verified exact; raw_fallback, observed 2026-08-07T12:08:02.382583Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 954456f8-4bf4-48d7-8406-c4d614839bae · outbound

This paper cites Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:58.929188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ea633dd-8b0e-4bc4-b856-61d281d5cb07 · outbound

This paper cites VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:59.063691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dacb2f80-318f-4ac3-bbe4-bcd682011472 · outbound

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

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:59.166840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad61aacc-e04c-4467-b7bc-20484df55abc · outbound

This paper cites an unresolved cited work.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:08:04.030424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3bf6bcac-375c-47b1-a898-025e275b64d8 · outbound

This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:59.394540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6ad0214-da61-4faf-9418-79d49ed2806d · outbound

This paper cites an unresolved cited work.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:59.467007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18052033-7682-4734-bb57-7241064fbeeb · outbound

This paper cites an unresolved cited work.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:59.540769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61896e90-9697-487d-97c9-d41d067afb22 · outbound

This paper cites an unresolved cited work.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:08:03.828294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 24c6b23a-9412-43a3-9f46-c68f6c612a63 · outbound

This paper cites an unresolved cited work.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:08:03.672537Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4706da89-891a-4ef9-96a2-1b119785f543 · outbound

This paper cites an unresolved cited work.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:08:03.534510Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 773f9717-8acf-4036-812e-db42a33c5dbe · outbound

This paper cites an unresolved cited work.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:08:03.382972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d6b9eb2a-688e-42fb-86e3-4432d33c29a2 · outbound

This paper cites an unresolved cited work.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:59.969474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b63719bd-e60e-4d8c-8b9e-fc5079bdf55a · outbound

This paper cites Jailbreaking Attack against Multimodal Large Language Model.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities Jailbreaking Attack against Multimodal Large Language Model

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T12:08:00.063288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1da87ad-cb78-4c6a-9a46-9b2070bb7952 · outbound

This paper cites an unresolved cited work.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:08:03.246576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 250f4292-1aaa-468b-a357-df2d3a13ba2a · outbound

This paper cites an unresolved cited work.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:08:03.132168Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 17532a42-0e7b-4c3f-b799-2eeae2f51478 · outbound

This paper cites Controlling Whisper: Universal Acoustic Adversarial Attacks to Control Speech Foundation Models.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities Controlling Whisper: Universal Acoustic Adversarial Attacks to Control Speech Foundation Models

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-08-07T12:08:02.097925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 21a7957e-c661-4c15-9b71-8bf8442eeff4 · outbound

This paper cites SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T12:08:00.473611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b231f7f-0ceb-4ee9-9267-943d30c1d320 · outbound

This paper cites an unresolved cited work.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T12:08:00.549823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ecc5970-7bc2-4fbf-9a5b-bfbb1ef7cc39 · outbound

This paper cites an unresolved cited work.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:08:02.955052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5828d487-26ed-4a7c-8d5e-e22c57919b19 · outbound

This paper cites A StrongREJECT for Empty Jailbreaks.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities A StrongREJECT for Empty Jailbreaks

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T12:08:00.711015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa713c1a-2c6d-4dff-88f3-d7e2ad255d43 · outbound

This paper cites an unresolved cited work.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T12:08:00.806008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ee29963-929a-482e-9b7c-c49704ecbde1 · outbound

This paper cites Hashimoto.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities Hashimoto

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T12:08:00.879017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4eed4580-7064-4eb6-ad56-239254d5fca0 · outbound

This paper cites an unresolved cited work.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:08:02.789674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b0392158-6983-49ac-a913-3a2e50c02009 · outbound

This paper cites $\textit{MMJ-Bench}$: A Comprehensive Study on Jailbreak Attacks and Defenses for Multimodal Large Language Models.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities $\textit{MMJ-Bench}$: A Comprehensive Study on Jailbreak Attacks and Defenses for Multimodal Large Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T12:08:01.063214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 533b588a-dc9f-4e1b-8067-5e1a181356c8 · outbound

This paper cites an unresolved cited work.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:08:02.654199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 86a9542d-5d9c-4fca-905f-6735b5b3a238 · outbound

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

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T12:08:01.270169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05aed257-3e04-46bc-bc0d-3b90eefcd4ac · outbound

This paper cites online" 'onlinestring :=.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities online" 'onlinestring :=

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T12:08:01.337660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdc45ecb-57f9-4e26-a6fd-13d499bd92a5 · outbound

This paper cites write newline.

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities write newline

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T12:08:01.411183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 70f892a0-c216-4f7b-bed9-7cf6f9b57923 · inbound

New Wide-Net-Casting Jailbreak Attacks Risk Large Models cites this paper.

New Wide-Net-Casting Jailbreak Attacks Risk Large Models Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-20T14:48:23.263188Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.