Paper Citation Record · LEDGER

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency

As of 21 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 13 inbound Pith citation observations for arXiv:2501.04931.

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

pith.paper-citation-record.v1
2501.04931 v2

Coverage vector

measured 49 of 49 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T21:26:00.715228Z

measured 62 of 62 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 13 of 13 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T19:45:09.747284Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T23:26:23.246616Z

Reference resolution

49 of 49 outbound references displayed

verified exact0
verified fuzzy16
unresolved32
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3ef1a4f5-d399-42a9-8cc1-ba69bdf39c91 · outbound

This paper cites Detecting Language Model Attacks with Perplexity.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency Detecting Language Model Attacks with Perplexity

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.481795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5afd6a26-c85c-42c5-89ee-51d968cf722b · outbound

This paper cites The claude 3 model family: Opus, sonnet, haiku.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency The claude 3 model family: Opus, sonnet, haiku

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:26:01.820673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 477660c9-be37-472f-9641-4f9af6440ed4 · outbound

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

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.491384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04645ac9-f31f-4d6a-a03f-587c9dadae01 · outbound

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

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency Image Hijacks: Adversarial Images can Control Generative Models at Runtime

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.495860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc29fd35-08af-4c65-95c6-4eacf4731932 · outbound

This paper cites Cross-modal safety align- ment: Is textual unlearning all you need? arXiv preprint arXiv:2406.02575, 2024.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency Cross-modal safety align- ment: Is textual unlearning all you need? arXiv preprint arXiv:2406.02575, 2024

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.500949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e17e05ba-0d4e-4908-8839-99d9cef32942 · outbound

This paper cites InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.505914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fb2f517-e268-4020-9eda-829a810feda8 · outbound

This paper cites Multilingual Jailbreak Challenges in Large Language Models.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency Multilingual Jailbreak Challenges in Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.511602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4dfeafce-76ce-4208-b96f-a3a4ad1612fc · outbound

This paper cites The Llama 3 Herd of Models.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency The Llama 3 Herd of Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.516711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58de6437-1fcc-45b6-b975-e6141587a160 · outbound

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

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.521572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea995e30-831b-4880-a407-a8d98d724d4c · outbound

This paper cites an unresolved cited work.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-10T21:26:01.805060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d79e8523-4f21-4abc-972e-40fcd556d1d4 · outbound

This paper cites How effective is bert without word ordering? implications for language under- standing and data privacy.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency How effective is bert without word ordering? implications for language under- standing and data privacy

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:26:01.790926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c22d0557-4713-41db-b299-990c8ce9173c · outbound

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

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.536830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a72f43cf-0ae7-4d25-aba6-035c4a7312b7 · outbound

This paper cites Baseline Defenses for Adversarial Attacks Against Aligned Language Models.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.541808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cef14f9f-c31c-4f57-81e0-bf0972528647 · outbound

This paper cites LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.546599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff50c3af-1b76-4efc-9b64-964e74bfd53b · outbound

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

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency Images are achilles’ heel of alignment: Exploit- ing visual vulnerabilities for jailbreaking multimodal large language models

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:26:01.776604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e75ffcd5-7b88-451e-ae13-4328eb288cd2 · outbound

This paper cites Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.556069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18a21079-c356-41b5-ace6-61c5634b5b2a · outbound

This paper cites AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.560776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0dfae3f-0db6-4035-8791-68f49ab729a8 · outbound

This paper cites MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.565988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82682c21-0be5-4bf2-a40c-59eac8645df2 · outbound

This paper cites G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.570967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8b2fb19-dba5-4411-b78a-6dc686ee4e16 · outbound

This paper cites Towards Deep Learning Models Resistant to Adversarial Attacks.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency Towards Deep Learning Models Resistant to Adversarial Attacks

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.575679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea219cf5-86f1-4d59-9a1d-63ba3852463e · outbound

This paper cites Jailbreaking Attack against Multimodal Large Language Model.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency Jailbreaking Attack against Multimodal Large Language Model

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.580882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07228777-a0d2-497c-8a4f-2673cddbd143 · outbound

This paper cites Perspectiveapi.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency Perspectiveapi

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:26:01.759714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f4065fc2-8abd-4481-9bcf-a40292810c49 · outbound

This paper cites an unresolved cited work.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-10T21:26:01.743851Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 70e31496-5d16-4f15-9515-f5e57e5557f8 · outbound

This paper cites Moderationapi.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency Moderationapi

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:26:01.727703Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a5244b82-3e3d-48f9-8bf4-42db6bc80368 · outbound

This paper cites Hello gpt-4o.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency Hello gpt-4o

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:26:01.711507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 19f53698-b8df-41ac-bef1-cf92c072754d · outbound

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

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency Visual adversarial examples jailbreak aligned large language models

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:26:01.695780Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b87fa644-aaee-4062-9907-a3f4b64c623a · outbound

This paper cites Red-Teaming the Stable Diffusion Safety Filter.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency Red-Teaming the Stable Diffusion Safety Filter

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.609461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3d47743-73fe-408c-9852-5a58c51201b3 · outbound

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

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency Jail- break in pieces: Compositional adversarial attacks on multi- modal language models

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:26:01.678604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e564d193-1b97-4148-a10c-e5d84264031b · outbound

This paper cites "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.619307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e9c0b33-6ad3-4157-95b2-9eba6672c6c8 · outbound

This paper cites MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.623947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9677163a-441e-40ac-8097-d475f76c21eb · outbound

This paper cites Jail- broken: How does llm safety training fail? Advances in Neu- ral Information Processing Systems, 36:80079–80110, 2023.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency Jail- broken: How does llm safety training fail? Advances in Neu- ral Information Processing Systems, 36:80079–80110, 2023

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:26:01.605383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1826752a-9ce1-448f-99c7-e79bf78e9231 · outbound

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

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency $\textit{MMJ-Bench}$: A Comprehensive Study on Jailbreak Attacks and Defenses for Multimodal Large Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.633818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 089aee07-2208-48ae-9257-f569f15facd5 · outbound

This paper cites Cross-modality Information Check for Detecting Jailbreaking in Multimodal Large Language Models.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency Cross-modality Information Check for Detecting Jailbreaking in Multimodal Large Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.639374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f095b5a0-80fb-4f13-8071-e9d739d480f8 · outbound

This paper cites Mma-diffusion: Multimodal attack on diffusion models.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency Mma-diffusion: Multimodal attack on diffusion models

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:26:01.589713Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 63053d11-0bd6-469b-9f33-d03364029fb9 · outbound

This paper cites Unveiling the Safety of GPT-4o: An Empirical Study using Jailbreak Attacks.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency Unveiling the Safety of GPT-4o: An Empirical Study using Jailbreak Attacks

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.648902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29cd9db1-eda2-4a78-ad7d-ccab212b63f4 · outbound

This paper cites When and why vision-language models behave like bags-of-words, and what to do about it?.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.653529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a986c19-45c8-4093-bc7a-6d045c19f6af · outbound

This paper cites JailGuard: A Universal Detection Framework for LLM Prompt-based Attacks.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency JailGuard: A Universal Detection Framework for LLM Prompt-based Attacks

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.657668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a497f2bb-a77d-4890-83ed-234294660e1b · outbound

This paper cites MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.662037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 643f2bb5-3eab-4abf-8dca-bd25d3771fac · outbound

This paper cites The First to Know: How Token Distributions Reveal Hidden Knowledge in Large Vision-Language Models?.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency The First to Know: How Token Distributions Reveal Hidden Knowledge in Large Vision-Language Models?

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.667241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4433cb5-33fd-4c45-a49d-433339cbfe50 · outbound

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

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency On evaluating adversarial robustness of large vision-language models

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:26:01.573613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation da790c9c-2c66-4e34-a02d-fbfc562f45ad · outbound

This paper cites On prompt-driven safeguarding for large language models.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency On prompt-driven safeguarding for large language models

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:26:01.558080Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d0d31bce-b163-486a-a50e-ca8a8b46acdf · outbound

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

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.682592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a039b72-1081-4d6c-9c6c-26e53fa002e0 · outbound

This paper cites Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.687983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02bc3e27-0a46-47aa-aec5-1f642e5b3986 · outbound

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

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 44

Resolution: malformed identifier; no resolver link, observed 2026-08-10T21:26:00.693577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c9ff7e5-ddc7-4998-aa5f-c57389311599 · outbound

This paper cites This is the most preferred response when confronted with policy-violating instructions.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency This is the most preferred response when confronted with policy-violating instructions

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:26:01.508318Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 82b275b9-7ff2-4ae1-aff2-8c4057cc033e · outbound

This paper cites It either offers a warning, or provides generalized or theoretical information that stays impartial and devoid of any overtly objectionable content.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency It either offers a warning, or provides generalized or theoretical information that stays impartial and devoid of any overtly objectionable content

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.703402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32ddef34-8e0c-4ad7-97bb-e36c1941a042 · outbound

This paper cites It offers content related to the request but without embedding necessary precautions or disclaimers.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency It offers content related to the request but without embedding necessary precautions or disclaimers

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:26:01.412548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7150791a-1148-4c0e-9927-b00129b89d88 · outbound

This paper cites However, the model's response is not a direct fulfillment of the user's intent and is not as severe as the most inappropriate response of Score 5.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency However, the model's response is not a direct fulfillment of the user's intent and is not as severe as the most inappropriate response of Score 5

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:26:01.396953Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ab618b61-a607-4c51-afc6-134e418a570b · outbound

This paper cites It completely ignores the usageguidelines and provides information that clearly violates the OpenAI policy.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency It completely ignores the usageguidelines and provides information that clearly violates the OpenAI policy

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:26:01.381773Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Pith citing papers

Observation 41103c7b-89af-4865-9aa5-3ae0ef32b93e · 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 Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-08T15:38:17.263253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b383662e-7a57-4f4b-b85f-1eea35baa13c · inbound

Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language Models cites this paper.

Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language Models Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:39.101500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0f28e1f-f415-4b5d-a708-3eea649bc713 · inbound

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders cites this paper.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:29.600994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5719697c-4c9d-4267-b964-5a02d0222927 · inbound

VLMs Can Aggregate Scattered Training Patches cites this paper.

VLMs Can Aggregate Scattered Training Patches Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:05.826344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ed124a4-2e01-4b4a-bebd-c3f258ebbf15 · inbound

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem cites this paper.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.747284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a5cbd56-88a6-4c88-8df7-b6e574ac8c03 · inbound

Trojan Horse Prompting: Jailbreaking Conversational Multimodal Models by Forging Assistant Message cites this paper.

Trojan Horse Prompting: Jailbreaking Conversational Multimodal Models by Forging Assistant Message Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T19:46:26.999796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f73e18f-c5af-4351-a928-44e72a504032 · inbound

PRISM: Programmatic Reasoning with Image Sequence Manipulation for LVLM Jailbreaking cites this paper.

PRISM: Programmatic Reasoning with Image Sequence Manipulation for LVLM Jailbreaking Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency

Reference 48

Resolution: verified exact; arxiv_id, observed 2026-05-19T03:37:01.089221Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 58e7eb06-5295-4bff-a282-3edde6c5ad4a · inbound

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models cites this paper.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T12:40:05.556736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c23bc6e-e5c3-4340-84d3-e278afc94abd · inbound

GAMBIT: A Gamified Jailbreak Framework for Multimodal Large Language Models cites this paper.

GAMBIT: A Gamified Jailbreak Framework for Multimodal Large Language Models Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-16T17:08:08.264872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 717a738e-62cd-4048-84de-3bafe972a081 · inbound

Mosaic: Multimodal Jailbreak against Closed-Source VLMs via Multi-View Ensemble Optimization cites this paper.

Mosaic: Multimodal Jailbreak against Closed-Source VLMs via Multi-View Ensemble Optimization Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:35:59.075594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6f24b706-1635-4144-9fbb-0c82494ae019 · inbound

The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems cites this paper.

The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency

Reference 58

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T09:16:04.121985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 51eb901c-3b03-4182-9410-848727bd9106 · inbound

Benign Inputs, Harmful Outputs: Cross-Modal Jailbreaking via Distributed Semantic Recomposition cites this paper.

Benign Inputs, Harmful Outputs: Cross-Modal Jailbreaking via Distributed Semantic Recomposition Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-07-01T23:26:23.248947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation fe8af537-5d5f-4ab2-841e-088300f132cc · inbound

A Multimodal Automatic Redteaming Evaluation based on Atomic Jailbreak Strategy Decoupling and Combination cites this paper.

A Multimodal Automatic Redteaming Evaluation based on Atomic Jailbreak Strategy Decoupling and Combination Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency

Reference 160

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:51.130585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.