Paper Citation Record · LEDGER

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders

As of 7 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2505.24519.

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

pith.paper-citation-record.v1
2505.24519 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:35:29.734144Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

37 of 37 outbound references displayed

verified exact3
verified fuzzy0
unresolved33
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e1b8b59c-2071-448b-9953-4396531b7cf8 · outbound

This paper cites online" 'onlinestring :=.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders online" 'onlinestring :=

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:25.933568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ec3fc88-97c6-44ed-89bc-6ffec363f147 · outbound

This paper cites write newline.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:25.982927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39107875-e453-4a4d-9130-873c64d3a0a4 · outbound

This paper cites GPT-4 Technical Report.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders GPT-4 Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:26.079150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccd595d5-669e-4bd3-b9d5-5f75e0235220 · outbound

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

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:26.166915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 482ab8ce-1631-47f2-ac94-31d182adad7e · outbound

This paper cites an unresolved cited work.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:35:31.713996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9519eda1-bd00-4a51-b2da-7a4555a3bfff · outbound

This paper cites DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:26.371851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2cbd348-5c46-4b5e-89c5-44af4ff6e641 · outbound

This paper cites an unresolved cited work.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:35:31.584942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 71bdcb01-8904-4e8f-96c7-830263e41da1 · outbound

This paper cites ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:26.553538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2da1b165-06a7-454d-b2b0-4971301913eb · outbound

This paper cites an unresolved cited work.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders Unresolved cited work

Reference 9

Resolution: metadata mismatch; raw_fallback, observed 2026-08-07T12:35:30.703721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation dcf6d652-8dbb-4351-829b-31ada64094cb · outbound

This paper cites Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:26.772719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15745a6e-fa80-4aa0-b09a-8879aa8366e6 · outbound

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

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:26.878499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34d5c27d-c373-4429-bc04-7021f7871f58 · outbound

This paper cites Eyes Closed, Safety On: Protecting Multimodal LLMs via Image-to-Text Transformation.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders Eyes Closed, Safety On: Protecting Multimodal LLMs via Image-to-Text Transformation

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:26.935873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 383440b7-5bbc-492a-812b-4f773c789803 · outbound

This paper cites WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:27.036330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 829353e0-621a-4b52-89c0-78ac6ac7e9c0 · outbound

This paper cites A Diagram Is Worth A Dozen Images.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders A Diagram Is Worth A Dozen Images

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:27.138684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b0f4459-02d0-447c-a4c4-cbe4f500a9b6 · outbound

This paper cites Improved Baselines with Visual Instruction Tuning.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders Improved Baselines with Visual Instruction Tuning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:27.244469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc9f6bfe-fd97-4e71-832b-1f1fccf337f9 · outbound

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

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:27.358332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b4b497e-7604-43f3-a40b-f86b1d603876 · outbound

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

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders Towards Deep Learning Models Resistant to Adversarial Attacks

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:27.438621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0f156a1-1c31-4c81-bd4e-6e068d4595a6 · outbound

This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:27.577719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5eb8da3-2fb5-4a0b-a87f-592c7f958673 · outbound

This paper cites InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-08-07T12:35:30.381649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f47762c9-4d25-41ad-b147-744e6e0ad953 · outbound

This paper cites The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:27.803525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aaec619b-8e1a-4d76-ad0a-f774bf657377 · outbound

This paper cites Visual Adversarial Examples Jailbreak Aligned Large Language Models.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders Visual Adversarial Examples Jailbreak Aligned Large Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:27.915330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4a215b9-c758-49c1-9c63-548fa95d2a35 · outbound

This paper cites Learning Transferable Visual Models From Natural Language Supervision.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders Learning Transferable Visual Models From Natural Language Supervision

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:28.065494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0aa3501a-d4ae-46ab-9dbc-fb8b7f141be9 · outbound

This paper cites High-Resolution Image Synthesis with Latent Diffusion Models.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders High-Resolution Image Synthesis with Latent Diffusion Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:28.220688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91e87091-4d6a-46ae-b4f2-9f348ae857a9 · outbound

This paper cites Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:28.325476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f84160e-c117-47a7-adf9-dc7131e81afb · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:28.439965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1749e4a-3499-471e-977b-bffb9a1376c6 · outbound

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

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-08-07T12:35:30.147706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d05710b4-f375-435f-bf7b-37595393caff · outbound

This paper cites an unresolved cited work.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:35:31.415390Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c64e1a0a-08d5-4cb2-94be-b018a4da1163 · outbound

This paper cites an unresolved cited work.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders Unresolved cited work

Reference 28

Resolution: verified exact; doi, observed 2026-08-07T12:35:29.943613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b8d999a5-3168-44d8-9a4f-025c2ed97d02 · outbound

This paper cites an unresolved cited work.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:35:31.251711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 92ed591e-d0b9-442d-9796-31b2a290a10c · outbound

This paper cites Retrieval-Augmented Perception: High-Resolution Image Perception Meets Visual RAG.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders Retrieval-Augmented Perception: High-Resolution Image Perception Meets Visual RAG

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:28.937202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16ca3de2-682f-40fc-873e-ac171a18bec1 · outbound

This paper cites an unresolved cited work.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:35:31.101861Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f8bc47bc-ec44-4cb8-81b7-a155ab253df6 · outbound

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

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:29.141982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbf8ac02-46f5-47c5-ad8e-267831a68839 · outbound

This paper cites VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:29.219653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12287ed5-b3a7-4724-a9f0-f073f7520f66 · outbound

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

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders JailGuard: A Universal Detection Framework for LLM Prompt-based Attacks

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:29.349854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9db12ec0-468f-4cdd-83ef-c4c15b7458d6 · outbound

This paper cites an unresolved cited work.

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:35:30.932001Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

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

This paper cites Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency.

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 f5cdf2a8-9de9-4834-88b0-95f27cc88802 · outbound

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

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:29.734144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.