Paper Citation Record · LEDGER

Securing Multimodal AI through Internal Information Decomposition

As of 21 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:2607.21600.

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

pith.paper-citation-record.v1
2607.21600 v1

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T15:03:01.447793Z

measured 33 of 33 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 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

33 of 33 outbound references displayed

verified exact0
verified fuzzy0
unresolved32
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation bfed0043-890a-426c-acdc-85bf21af107d · outbound

This paper cites Qwen2.5-VL Technical Report.

Securing Multimodal AI through Internal Information Decomposition Qwen2.5-VL Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T15:02:57.997161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb55d4c7-79ef-447a-bbda-92082a225337 · outbound

This paper cites Jailbreaking Black Box Large Language Models in Twenty Queries.

Securing Multimodal AI through Internal Information Decomposition Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T15:02:58.279711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fae3157-4b5f-4e72-bb97-188145f8b5f4 · outbound

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

Securing Multimodal AI through Internal Information Decomposition DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T15:02:58.424519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96fa12cc-2f83-4a58-8df5-53b3942d1379 · outbound

This paper cites The Llama 3 Herd of Models.

Securing Multimodal AI through Internal Information Decomposition The Llama 3 Herd of Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T15:02:58.674459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f8ff18d-7e5c-45ad-b0f2-054ff7dce504 · outbound

This paper cites MirrorCheck: Efficient Adversarial Defense for Vision-Language Models.

Securing Multimodal AI through Internal Information Decomposition MirrorCheck: Efficient Adversarial Defense for Vision-Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T15:02:58.880122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfae213e-9029-4b58-954f-127a92ef4fd2 · outbound

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

Securing Multimodal AI through Internal Information Decomposition FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T15:02:59.139372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4e52eaa-f2ca-4f87-a83d-25ed95e7954b · outbound

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

Securing Multimodal AI through Internal Information Decomposition Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T15:02:59.641888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2444ea51-84c0-4ece-8723-71219482be7c · outbound

This paper cites AI Alignment: A Comprehensive Survey.

Securing Multimodal AI through Internal Information Decomposition AI Alignment: A Comprehensive Survey

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T15:02:59.770853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a60bd29-46b3-4948-80b1-9a2723b30304 · outbound

This paper cites ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs.

Securing Multimodal AI through Internal Information Decomposition ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T15:02:59.892345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af7ba74a-be5b-4a97-b870-8f56b06562df · outbound

This paper cites Gemma 3 Technical Report.

Securing Multimodal AI through Internal Information Decomposition Gemma 3 Technical Report

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T15:02:59.953206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61c847a2-bb09-4873-9bf1-2e5d82d57f48 · outbound

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

Securing Multimodal AI through Internal Information Decomposition MOSSBench: Is Your Multimodal Language Model Oversensitive to Safe Queries?

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T15:03:00.136710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cc2164e-9968-467e-affb-a0cd047c6307 · outbound

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

Securing Multimodal AI through Internal Information Decomposition MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T15:03:00.273991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffa5c034-8062-4550-bd25-f6d4e4260c05 · outbound

This paper cites Jailbreaking Attack against Multimodal Large Language Model.

Securing Multimodal AI through Internal Information Decomposition Jailbreaking Attack against Multimodal Large Language Model

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T15:03:00.340843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d3eb570-0db1-450a-9faa-31f9349b4926 · outbound

This paper cites Qi, X., Huang, K., Panda, A., Henderson, P., Wang, M., and Mittal, P.

Securing Multimodal AI through Internal Information Decomposition Qi, X., Huang, K., Panda, A., Henderson, P., Wang, M., and Mittal, P

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T15:03:00.455003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec5622d3-6877-43fe-9108-89fb88938cc3 · outbound

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

Securing Multimodal AI through Internal Information Decomposition Visual Adversarial Examples Jailbreak Aligned Large Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T15:03:00.459707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0637691e-9c18-48c5-b8f6-28cad3c7f5d0 · outbound

This paper cites Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack.

Securing Multimodal AI through Internal Information Decomposition Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T15:03:00.463918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fe2a1f3-7795-4fba-bf02-8caf1827bc63 · outbound

This paper cites White-box Multimodal Jailbreaks Against Large Vision-Language Models.

Securing Multimodal AI through Internal Information Decomposition White-box Multimodal Jailbreaks Against Large Vision-Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T15:03:00.706850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f94b3422-f9f0-4a29-9320-cfe54fc14c0a · outbound

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

Securing Multimodal AI through Internal Information Decomposition Cross-modality Information Check for Detecting Jailbreaking in Multimodal Large Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T15:03:00.946530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ad33a52-c565-4179-939f-d7dbe3f20c75 · outbound

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

Securing Multimodal AI through Internal Information Decomposition Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T15:03:01.071423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e476ad4f-e8be-4651-acc9-85456b71fbec · outbound

This paper cites Sure, here is.

Securing Multimodal AI through Internal Information Decomposition Sure, here is

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T15:03:01.447793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6062de3d-fc1a-4f6b-8fb0-c006037ee109 · outbound

This paper cites DO NOT include harmful content in your response.

Securing Multimodal AI through Internal Information Decomposition DO NOT include harmful content in your response

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-02T15:03:01.161001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9c94644-0f7a-4a88-a735-dae0811e211c · outbound

This paper cites Wang, R., Ma, X., Zhou, H., Ji, C., Ye, G., and Jiang, Y .-G.

Securing Multimodal AI through Internal Information Decomposition Wang, R., Ma, X., Zhou, H., Ji, C., Ye, G., and Jiang, Y .-G

Reference 1948

Resolution: unresolved; no resolver link, observed 2026-08-02T15:03:00.540725Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab658a34-554d-418a-bcf4-2c30d29b46f1 · outbound

This paper cites URL https: //doi.org/10.1214/aoms/1177729694.

Securing Multimodal AI through Internal Information Decomposition URL https: //doi.org/10.1214/aoms/1177729694

Reference 1951

Resolution: unresolved; no resolver link, observed 2026-08-02T15:03:00.062036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa6fd3a5-09c8-457f-a81c-a5cd20f99af6 · outbound

This paper cites an unresolved cited work.

Securing Multimodal AI through Internal Information Decomposition Unresolved cited work

Reference 1991

Resolution: unresolved; no resolver link, observed 2026-08-02T15:03:00.177513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8c1bf3a-9aed-4b8e-b11c-bec0be5d92af · outbound

This paper cites Liu, H., Li, C., Wu, Q., and Lee, Y.

Securing Multimodal AI through Internal Information Decomposition Liu, H., Li, C., Wu, Q., and Lee, Y

Reference 2008

Resolution: unresolved; no resolver link, observed 2026-08-02T15:03:00.218077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d5fac30-f0f0-4694-aa3b-0f859aca3f84 · outbound

This paper cites Nonnegative Decomposition of Multivariate Information.

Securing Multimodal AI through Internal Information Decomposition Nonnegative Decomposition of Multivariate Information

Reference 2010

Resolution: unresolved; no resolver link, observed 2026-08-02T15:03:00.847790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bb3ef10-f102-4b69-a523-97760ede7fa3 · outbound

This paper cites Sure, here is.

Securing Multimodal AI through Internal Information Decomposition Sure, here is

Reference 2017

Resolution: malformed identifier; no resolver link, observed 2026-08-02T15:03:01.282759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f34e6295-32c8-4142-9545-491416e1ed38 · outbound

This paper cites VizWiz Grand Challenge: Answering Visual Questions from Blind People.

Securing Multimodal AI through Internal Information Decomposition VizWiz Grand Challenge: Answering Visual Questions from Blind People

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-02T15:02:59.292875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de3c4701-412d-4acb-8dd5-e3329bb092c8 · outbound

This paper cites Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks.

Securing Multimodal AI through Internal Information Decomposition Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-02T15:02:58.558426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e855e13-e178-4aaf-b694-1148474964e4 · outbound

This paper cites doi: 10.18653/v1/2021.acl-long.133.

Securing Multimodal AI through Internal Information Decomposition doi: 10.18653/v1/2021.acl-long.133

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-02T15:02:59.013034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cab09187-d374-4a72-a880-d9f0b90a66df · outbound

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

Securing Multimodal AI through Internal Information Decomposition Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-02T15:02:59.499483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bac76bc1-07cc-4137-a403-25d788855de2 · outbound

This paper cites Discovering Latent Knowledge in Language Models Without Supervision.

Securing Multimodal AI through Internal Information Decomposition Discovering Latent Knowledge in Language Models Without Supervision

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-02T15:02:58.141704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bcf0487-a5b7-4e05-b895-f080ab07ecd6 · outbound

This paper cites an unresolved cited work.

Securing Multimodal AI through Internal Information Decomposition Unresolved cited work

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-02T15:02:57.887684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.