Paper Citation Record · LEDGER

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models

As of 9 August 2026, this Paper Citation Record lists 78 of 78 outbound references and 4 inbound Pith citation observations for arXiv:2505.23793.

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

pith.paper-citation-record.v1
2505.23793 v1

Coverage vector

measured 78 of 78 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:15:20.372542Z

measured 82 of 82 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-28T18:20:43.092561Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T17:37:14.921452Z

Reference resolution

78 of 78 outbound references displayed

verified exact0
verified fuzzy30
unresolved48
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 986062ee-f95d-4231-89c6-0ff4c9080126 · outbound

This paper cites Bert: Pre-training of deep bidirectional transformers for language understanding,.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Bert: Pre-training of deep bidirectional transformers for language understanding,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:30.449940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 30d901d3-4ea7-4456-a82c-65507ac437b3 · outbound

This paper cites GPT-4 Technical Report.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models GPT-4 Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:12.628526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d5e1484-76c8-4375-94c7-e64909df2901 · outbound

This paper cites A Survey of Large Language Models.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models A Survey of Large Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:12.839230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01347fd3-8a8a-42ce-99ab-5f21d18c58b3 · outbound

This paper cites A survey of graph retrieval-augmented generation for customized large language models,.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models A survey of graph retrieval-augmented generation for customized large language models,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:13.588175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce125e67-c302-4f6c-aad7-14a37aa53739 · outbound

This paper cites Entity alignment with noisy annotations from large language models,.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Entity alignment with noisy annotations from large language models,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:30.270519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c33d44fe-eecf-4fac-958a-8e3754a80d94 · outbound

This paper cites Differentiable neuro-symbolic reason- ing on large-scale knowledge graphs,.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Differentiable neuro-symbolic reason- ing on large-scale knowledge graphs,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:30.164673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 792c852f-1151-4710-90d4-5a20d32e9ccb · outbound

This paper cites A Survey on Benchmarks of Multimodal Large Language Models.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models A Survey on Benchmarks of Multimodal Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:13.867592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67256299-27b6-4bb2-93c7-fa0bee446f3c · outbound

This paper cites GPT-4o System Card.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models GPT-4o System Card

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:13.984441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0065e08-f2df-45df-9798-2e54cc942b1c · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:14.127721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a41746f6-c695-405c-87a4-f2817a9eaf7f · outbound

This paper cites RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:14.184417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c2bc979-887e-44a9-92b6-a714c3824eb2 · outbound

This paper cites Multimodal Situational Safety.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Multimodal Situational Safety

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:14.292317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3392940-f091-44ea-af6f-02bd69465498 · outbound

This paper cites JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:14.365288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bc9debb-bd60-4834-aa74-c78e0cfae01f · outbound

This paper cites MM-SafetyBench: A benchmark for safety evaluation of multimodal large language models,.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models MM-SafetyBench: A benchmark for safety evaluation of multimodal large language models,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:30.078912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3073b0e2-b04e-4ea1-b241-861c3677159f · outbound

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

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Images are achilles’ heel of alignment: Exploiting visual vulnerabilities for jailbreaking multimodal large language models,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:29.901591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 81224b51-d815-4cc8-b8d6-ff80d131f6cc · outbound

This paper cites HarmBench: A standardized evaluation framework for automated red teaming and robust refusal,.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models HarmBench: A standardized evaluation framework for automated red teaming and robust refusal,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:29.583738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e7377fa6-6833-4e98-b11b-30988793a172 · outbound

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

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:14.653615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bad3ab9-b982-4dec-b1b5-0c6a2b0f5136 · outbound

This paper cites VLSBench: Unveiling Visual Leakage in Multimodal Safety.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models VLSBench: Unveiling Visual Leakage in Multimodal Safety

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:14.746223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b48dfcef-a75e-4f09-bc53-c11b55f00d6b · outbound

This paper cites MOSSBench: Is Your Multimodal Language Model Oversensitive to Safe Queries?.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models MOSSBench: Is Your Multimodal Language Model Oversensitive to Safe Queries?

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:14.833561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11031a20-8e20-4e19-a806-c1974e1becf0 · outbound

This paper cites MLLMGuard: A multi-dimensional safety evaluation suite for multimodal large language models,.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models MLLMGuard: A multi-dimensional safety evaluation suite for multimodal large language models,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:29.347012Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f18a4617-51f3-489e-9865-bd2b81a2d2d0 · outbound

This paper cites Red teaming visual language models,.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Red teaming visual language models,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:29.099603Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a5d1d146-28b3-4733-ba5a-9ebf9c15d481 · outbound

This paper cites DRESS : Instructing large vision- language models to align and interact with humans via natural language feedback,.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models DRESS : Instructing large vision- language models to align and interact with humans via natural language feedback,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:28.851380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c8b74500-d09d-4033-8f3b-8dfcfc51f3cd · outbound

This paper cites Safety fine-tuning at (almost) no cost: A baseline for vision large language models,.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Safety fine-tuning at (almost) no cost: A baseline for vision large language models,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:28.572555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4c35aa6d-af23-4ccd-b6cd-39e70e21f35e · outbound

This paper cites SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:15.211995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6bd229b-582d-4536-895f-3708f8ddd20a · outbound

This paper cites How many are in this image a safety evaluation benchmark for vision LLMs,.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models How many are in this image a safety evaluation benchmark for vision LLMs,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:28.333140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c95c9956-7f2b-464b-bbfe-63974186c09d · outbound

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

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:15.423021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66186c82-d55c-423e-96fa-50548104765b · outbound

This paper cites Chinese SafetyQA: A Safety Short-form Factuality Benchmark for Large Language Models.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Chinese SafetyQA: A Safety Short-form Factuality Benchmark for Large Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:15.522766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9942e338-8dd3-41aa-b0c4-7e0716be7eab · outbound

This paper cites Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:15.592961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 469ee958-be37-46fc-967a-b552d5253e39 · outbound

This paper cites Cross-Modal safety alignment: Is textual unlearning all you need?.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Cross-Modal safety alignment: Is textual unlearning all you need?

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:15.658237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e94f7f0-b9f1-4f6f-aa6c-9f44d050fd51 · outbound

This paper cites LLM-Fuzzer: Scaling assessment of large language model jailbreaks,.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models LLM-Fuzzer: Scaling assessment of large language model jailbreaks,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:28.055383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 12fd0605-b6cb-4cf2-98c4-ec50ad46269e · outbound

This paper cites Qwen2.5-VL Technical Report.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Qwen2.5-VL Technical Report

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:15.790380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 584eb1e0-8a8a-4015-bf63-db8eddbf9bf4 · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:15.831513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c3b4aee-13d0-4b6e-8495-7dd0a6489a59 · outbound

This paper cites How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:15.950936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44b720f6-b940-4a8e-bf8f-7a927eaee84d · outbound

This paper cites InternVL: Scaling up vision foundation models and aligning for generic visual-linguistic tasks,.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models InternVL: Scaling up vision foundation models and aligning for generic visual-linguistic tasks,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:27.839847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5c6bafc3-e54b-41de-865c-cacaf0f26551 · outbound

This paper cites ChatGLM: A family of large language models from GLM-130B to GLM-4 all tools,.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models ChatGLM: A family of large language models from GLM-130B to GLM-4 all tools,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:27.724643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9a3db7f5-09ba-44fc-89ea-b2b29b711365 · outbound

This paper cites CogVLM: Visual expert for pretrained language models,.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models CogVLM: Visual expert for pretrained language models,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:27.601596Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 88ca9d66-a048-413d-8a7c-94986e8adccf · outbound

This paper cites Improved baselines with visual instruction tuning,.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Improved baselines with visual instruction tuning,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:27.479504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation dcb64f2c-9b35-48e2-8990-2a95b70739df · outbound

This paper cites MiniCPM-V: A GPT-4V Level MLLM on Your Phone.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models MiniCPM-V: A GPT-4V Level MLLM on Your Phone

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:16.297715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bae5c4d4-73f8-4885-93c2-c8d5a8e0b41b · outbound

This paper cites VILA: On pre-training for visual language models,.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models VILA: On pre-training for visual language models,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:27.243892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1b70f732-d3e6-4a73-8736-eecd3ef6a7f5 · outbound

This paper cites NVILA: Efficient frontier visual language models,.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models NVILA: Efficient frontier visual language models,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:26.979657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation eab92bbe-8d41-4d25-9cb5-19608c97392f · outbound

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

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Scaling rectified flow transformers for high-resolution image synthesis,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:26.734339Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 58d6533d-1d97-4cbb-9e42-89d1ae3c0367 · outbound

This paper cites an unresolved cited work.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Unresolved cited work

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:16.552545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b78774f6-cb58-4c3e-9367-9c11b0d1f465 · outbound

This paper cites Visual instruction tuning,.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Visual instruction tuning,

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:16.637934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac976ac2-e652-4067-b122-99dc91ce8491 · outbound

This paper cites Equilibrate RLHF: Towards Balancing Helpfulness-Safety Trade-off in Large Language Models.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Equilibrate RLHF: Towards Balancing Helpfulness-Safety Trade-off in Large Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:16.718554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe0f0a71-571a-48fb-be9b-dc635c57f7cb · outbound

This paper cites SafetyBench: Evaluating the Safety of Large Language Models.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models SafetyBench: Evaluating the Safety of Large Language Models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:16.805123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a83e0c6c-d4cb-4578-aa51-2c54070e2d61 · outbound

This paper cites R-Judge: Benchmarking Safety Risk Awareness for LLM Agents.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models R-Judge: Benchmarking Safety Risk Awareness for LLM Agents

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:16.892095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94b3aef8-1d9f-4329-9fb6-cde640ea49e5 · outbound

This paper cites HiddenDetect: Detecting Jailbreak Attacks against Large Vision-Language Models via Monitoring Hidden States.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models HiddenDetect: Detecting Jailbreak Attacks against Large Vision-Language Models via Monitoring Hidden States

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:16.955465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59f00c4c-c6f5-444f-90d6-ac3def44a7d3 · outbound

This paper cites B-AVIBench: Towards Evaluating the Robustness of Large Vision-Language Model on Black-box Adversarial Visual-Instructions.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models B-AVIBench: Towards Evaluating the Robustness of Large Vision-Language Model on Black-box Adversarial Visual-Instructions

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:17.045515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b2999f1-0081-45a8-8d5a-cf96aa11acf1 · outbound

This paper cites SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:17.144248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b5040a8-d1ac-4361-bbbe-a32493985afe · outbound

This paper cites Microsoft CoCo: Common objects in context,.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Microsoft CoCo: Common objects in context,

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:26.458441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ede9c498-04e1-48dd-98ed-376afa6925ba · outbound

This paper cites Laion-5b: An open large-scale dataset for training next generation image-text models,.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Laion-5b: An open large-scale dataset for training next generation image-text models,

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:26.197086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f2d3928f-b10f-4c40-9cff-96e6c280a641 · outbound

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

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models FigStep: Jailbreaking large vision-language models via typographic visual prompts,

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:25.942318Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b956f090-6f6d-4986-8930-bd19d7a3974f · outbound

This paper cites an unresolved cited work.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Unresolved cited work

Reference 52

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:15:25.637777Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation fa473ae0-59c9-4aa4-9336-2b3a22132fa8 · outbound

This paper cites an unresolved cited work.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Unresolved cited work

Reference 53

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:15:25.410682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e5da0302-eb48-44a4-abc2-523e3918c645 · outbound

This paper cites Here are some examples: Example 1: [Input] First category: Personal Rights & Property Second category: Personal Injury [Output].

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Here are some examples: Example 1: [Input] First category: Personal Rights & Property Second category: Personal Injury [Output]

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:25.249072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 94ef1918-e658-4e43-a043-7669baf90735 · outbound

This paper cites an unresolved cited work.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Unresolved cited work

Reference 55

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:15:25.040165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ad843633-ab21-4b7f-bd3e-fb2875175471 · outbound

This paper cites an unresolved cited work.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Unresolved cited work

Reference 56

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:15:24.882679Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d3ea8b28-4da3-4a95-ab07-ce9553293b23 · outbound

This paper cites Example 2: [Input] First category: Network Attacks Second category: Phishing Email Guidance [Output].

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Example 2: [Input] First category: Network Attacks Second category: Phishing Email Guidance [Output]

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:24.682441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation dca17653-ee8d-4f23-9f22-ab31e5e092b6 · outbound

This paper cites an unresolved cited work.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Unresolved cited work

Reference 58

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:15:24.541842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9dd61599-8aa1-4187-99bc-3c49b3876be7 · outbound

This paper cites an unresolved cited work.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Unresolved cited work

Reference 59

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:15:24.379352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1a42226f-ce5b-466a-a8cf-40bb3f21bc26 · outbound

This paper cites an unresolved cited work.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Unresolved cited work

Reference 60

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:15:24.171243Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 26ba96af-471e-4cc5-9675-0a732226f923 · outbound

This paper cites Or, the image should detail depict some harmful objects.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Or, the image should detail depict some harmful objects

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:23.994776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 22301e9c-2e12-40bb-9136-b0e222440405 · outbound

This paper cites Make sure that the harmful queries should directly or indirectly lead to harmful output.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Make sure that the harmful queries should directly or indirectly lead to harmful output

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:23.815050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a16ed69f-4346-41dd-8999-1e5aae0d9010 · outbound

This paper cites an unresolved cited work.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Unresolved cited work

Reference 63

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:15:23.636609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation bdd5bb1d-1f55-48df-824a-7013cf967b9c · outbound

This paper cites an unresolved cited work.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Unresolved cited work

Reference 64

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:15:23.429985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a1d4ca31-1a26-4ef5-84ef-cd69dd24cc82 · outbound

This paper cites an unresolved cited work.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Unresolved cited work

Reference 65

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:15:23.214665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1b7c69d1-b984-46c7-9580-167935410044 · outbound

This paper cites an unresolved cited work.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Unresolved cited work

Reference 66

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:15:23.020126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1c9998c3-216a-44bc-b285-0313f8eb3704 · outbound

This paper cites Then, you must provide an explanation and a refined T2I prompt.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Then, you must provide an explanation and a refined T2I prompt

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:22.869712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 79e2d5de-9e56-4ca1-aebf-cc1c170b0d05 · outbound

This paper cites an unresolved cited work.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Unresolved cited work

Reference 68

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:15:22.778346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 197402b8-de20-488d-9b95-3c6f18e7c571 · outbound

This paper cites marijuana.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models marijuana

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:22.619380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f739252a-cb13-409f-a6fb-bd398ffda537 · outbound

This paper cites an unresolved cited work.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Unresolved cited work

Reference 70

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:15:22.433160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d50a1a3b-5bfd-4b08-bcd5-6bc925bf0d2b · outbound

This paper cites an unresolved cited work.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Unresolved cited work

Reference 71

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:15:22.222796Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9111cf0a-86a5-4f5b-8581-c888f631294b · outbound

This paper cites Refusal includes responses that only offer alternative suggestions without answering the original request.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Refusal includes responses that only offer alternative suggestions without answering the original request

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:21.992660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e45eb8fa-4eff-45b9-903a-9959fbb7e410 · outbound

This paper cites an unresolved cited work.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Unresolved cited work

Reference 73

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:15:21.837203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0804baef-0860-4e33-8d82-5fe5d901b186 · outbound

This paper cites an unresolved cited work.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Unresolved cited work

Reference 74

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:15:21.689030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d3f2d60a-285d-48b8-8f63-e9c9d07f3c45 · outbound

This paper cites an unresolved cited work.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Unresolved cited work

Reference 75

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:15:21.552026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c53906c0-5c64-4d72-8e95-d81b323c91e8 · outbound

This paper cites an unresolved cited work.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Unresolved cited work

Reference 76

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:15:21.448870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2a7d2394-9dc0-4a7e-a325-2b1eea3fae89 · outbound

This paper cites an unresolved cited work.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Unresolved cited work

Reference 77

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:15:21.349871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 68d3c54a-bb21-4428-90d5-6caeeeb18a6b · outbound

This paper cites Text Harmful.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models Text Harmful

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:15:21.144701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Pith citing papers

Observation bf60bcae-3289-43d1-9642-c2c0cab2c925 · inbound

SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems cites this paper.

SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-11T06:31:02.127072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8ca0d28b-5903-48c7-a60a-e93e6ee7f1bd · inbound

ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety cites this paper.

ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models

Reference 194

Resolution: verified exact; arxiv_id, observed 2026-05-11T12:46:05.639870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b9999ff2-1afe-4dd8-840e-cac435d6fb01 · inbound

MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation cites this paper.

MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models

Reference 72

Resolution: verified exact; arxiv_id, observed 2026-06-28T20:42:37.979654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 102e5780-ec6b-417b-895e-a62c1dd7e942 · inbound

Defending Jailbreak Attacks on Large Language Models via Manifold Trajectory Kinetics cites this paper.

Defending Jailbreak Attacks on Large Language Models via Manifold Trajectory Kinetics USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models

Reference 60

Resolution: verified exact; arxiv_id, observed 2026-07-02T17:37:14.923132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.