Paper Citation Record · LEDGER

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

As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 31 inbound Pith citation observations for arXiv:2405.20773.

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

pith.paper-citation-record.v1
2405.20773 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 31 of 31 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00

measured 31 of 31 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-12T14:24:32.531856Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 275cc0c3-64c3-4bdd-923c-e4d1691b24e5 · inbound

Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks cites this paper.

Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-12T14:24:32.531856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3b24ad5-4c12-46d1-ba32-413f9cc03941 · inbound

Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language Models cites this paper.

Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language Models Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T10:32:28.295755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d06010ab-dcd7-464f-9472-a6daabaff6c6 · inbound

Mirage in the Eyes: Hallucination Attack on Multi-modal Large Language Models with Only Attention Sink cites this paper.

Mirage in the Eyes: Hallucination Attack on Multi-modal Large Language Models with Only Attention Sink Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-10T14:29:28.074482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11d35ee0-45f9-4f58-9bdd-aea793577148 · inbound

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety cites this paper.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 283

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:34.086175Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 631adf9a-90c7-43e1-ae22-9610b9e7c1ea · inbound

When Data Manipulation Meets Attack Goals: An In-depth Survey of Attacks for VLMs cites this paper.

When Data Manipulation Meets Attack Goals: An In-depth Survey of Attacks for VLMs Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-08T15:38:17.089320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7fb9fc0-da95-4b8a-b745-96f5d8022a25 · inbound

Universal Adversarial Attack on Aligned Multimodal LLMs cites this paper.

Universal Adversarial Attack on Aligned Multimodal LLMs Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-08T11:17:01.654636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2983a16f-e1b5-4204-a268-c3055cc3eced · inbound

A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations cites this paper.

A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 105

Resolution: unresolved; no resolver link, observed 2026-08-07T19:45:19.478474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e654e81-4eeb-4fc4-9474-7c49d04a16fd · inbound

RedDiffuser: Auditing Multimodal Safety Failures in Vision-Language Models via Reinforced Diffusion cites this paper.

RedDiffuser: Auditing Multimodal Safety Failures in Vision-Language Models via Reinforced Diffusion Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-23T00:15:14.824301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation db1cdf8a-433a-4028-a163-02d76706a3b6 · inbound

Backdoor Cleaning without External Guidance in MLLM Fine-tuning cites this paper.

Backdoor Cleaning without External Guidance in MLLM Fine-tuning Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T14:56:53.654176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e8cf2df-b10e-489a-ac96-bc15025f4f03 · inbound

Towards medical AI misalignment: a preliminary study cites this paper.

Towards medical AI misalignment: a preliminary study Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T14:52:15.961141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 175db9d6-728f-4140-a7eb-cb7830d3e6b1 · inbound

Seeing the Threat: Vulnerabilities in Vision-Language Models to Adversarial Attack cites this paper.

Seeing the Threat: Vulnerabilities in Vision-Language Models to Adversarial Attack Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T13:22:01.801888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2d64ec6-2de9-4e5a-b235-bc0f4f94626a · inbound

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 cites this paper.

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:13.747840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9874aa5-95cf-4190-b522-76878372fe42 · inbound

Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM cites this paper.

Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 184

Resolution: unresolved; no resolver link, observed 2026-08-05T23:13:05.101293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7427c66f-c0ee-49c1-b825-77a9ac21efee · inbound

The First Differentiable Transfer-Based Algorithm for Discrete MicroLED Repair cites this paper.

The First Differentiable Transfer-Based Algorithm for Discrete MicroLED Repair Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T22:21:02.811865Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0fab43f-50a9-42b8-9577-5e536a723db5 · inbound

Blockchain Network Analysis using Quantum Inspired Graph Neural Networks & Ensemble Models cites this paper.

Blockchain Network Analysis using Quantum Inspired Graph Neural Networks & Ensemble Models Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-05T21:22:37.649627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 507b2e82-a73e-4034-8334-7fa17ee9e1e8 · inbound

Empowering Multimodal LLMs with External Tools: A Comprehensive Survey cites this paper.

Empowering Multimodal LLMs with External Tools: A Comprehensive Survey Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 231

Resolution: unresolved; no resolver link, observed 2026-08-05T20:29:06.482070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 672e6be8-72ed-474c-b237-579cc9d71b9e · inbound

On Surjectivity of Neural Networks: Can you elicit any behavior from your model? cites this paper.

On Surjectivity of Neural Networks: Can you elicit any behavior from your model? Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-05T16:00:48.746871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5be7c2a-2861-4dfc-a5c9-102b6a476f91 · inbound

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses cites this paper.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 133

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:50.007530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models cites this paper.

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 f036b930-a299-47f6-ba77-7ab84fc7cea0 · inbound

Multi-Turn Adaptive Prompting Attack on Large Vision-Language Models cites this paper.

Multi-Turn Adaptive Prompting Attack on Large Vision-Language Models Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T23:16:36.824638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f22ac78a-055d-4254-a4df-a8e26b4706be · inbound

Making MLLMs Blind: Adversarial Smuggling Attacks in MLLM Content Moderation cites this paper.

Making MLLMs Blind: Adversarial Smuggling Attacks in MLLM Content Moderation Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T00:45:50.274862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 92aad731-47a5-4fca-8760-fc4a54da3ee5 · inbound

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs cites this paper.

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 59

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:35:57.164743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 83a652be-a6d8-4526-9a4e-2fc782028d26 · inbound

Targeted Interpretable Safety Neuron Enhancement for Multilingual Vision-Language Large Models cites this paper.

Targeted Interpretable Safety Neuron Enhancement for Multilingual Vision-Language Large Models Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:20:58.246993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 5e4b0086-e642-4c06-9d0b-98d122104444 · inbound

Targeted Interpretable Safety Neuron Enhancement for Multilingual Vision-Language Large Models cites this paper.

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T16:34:05.343320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ae55dc8-cbca-449b-a83a-7bd0208d6261 · inbound

Through the Lens of Character: Resolving Modality-Role Interference in Multimodal Role-Playing Agent cites this paper.

Through the Lens of Character: Resolving Modality-Role Interference in Multimodal Role-Playing Agent Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-12T05:51:27.691230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation c8fc2ab4-fa70-42b6-b1e0-179ecf95f63e · inbound

Localization then Neutralization: Gradient-guided Token Suppression against Visual Prompt Injection Attack cites this paper.

Localization then Neutralization: Gradient-guided Token Suppression against Visual Prompt Injection Attack Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T12:24:39.790379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 7a59e5e3-7b94-4e75-b435-471ac28639ca · inbound

MLingualFC: Evaluating Jailbreak Vulnerabilities in Multilingual Vision-Language Models cites this paper.

MLingualFC: Evaluating Jailbreak Vulnerabilities in Multilingual Vision-Language Models Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 103

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T18:57:16.800737Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 883b4f59-0aa4-434a-8c3e-0dd1f017de4b · inbound

Adversarial Diffusion Across Modalities: A Fusion Survey of Attacks, Defenses, and Evaluation for Text, Vision, and Vision-Language Models cites this paper.

Adversarial Diffusion Across Modalities: A Fusion Survey of Attacks, Defenses, and Evaluation for Text, Vision, and Vision-Language Models Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-06-26T04:38:59.119984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 8d8a2ab6-d404-41d3-971f-ace533de2ab2 · inbound

V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure cites this paper.

V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T08:23:25.911168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e46ab36-d070-4706-8c15-0307e586e9e0 · inbound

The Mirage of LLM Guardrails: A Case Study in AI-Assisted Medical Note Manipulation cites this paper.

The Mirage of LLM Guardrails: A Case Study in AI-Assisted Medical Note Manipulation Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-30T20:22:15.367808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07a487c6-9b7a-4608-b51e-29d8e149ba68 · inbound

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs cites this paper.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-31T23:07:39.941483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.