Paper Citation Record · LEDGER

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM

As of 8 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 1 inbound Pith citation observation for arXiv:2507.20994.

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

pith.paper-citation-record.v1
2507.20994 v1

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T13:08:12.831013Z

measured 37 of 37 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T12:39:34.092556Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T12:39:34.185319Z

Reference resolution

36 of 36 outbound references displayed

verified exact0
verified fuzzy27
unresolved9
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0e6a83ea-ea1e-47ec-b23c-9ca53f94cf26 · outbound

This paper cites GPT-4 Technical Report.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T13:08:07.970072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5263691d-3b1f-4608-b5ab-8d8735dfa6e2 · outbound

This paper cites Nsfw image classification - resnet50.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM Nsfw image classification - resnet50

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:08:15.759539Z

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 2bf3a9c5-6aeb-4a5e-b6aa-255e719081b6 · outbound

This paper cites Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond, 2023.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond, 2023

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T13:08:08.282747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd1127be-6612-48af-9883-3652bffc30fe · outbound

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

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM Dress: Instructing large vision-language models to align and interact with humans via natural language feedback

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:08:15.691502Z

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 0e8caeda-72f3-4a8d-86ce-32eefff1208e · outbound

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

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:08:15.638904Z

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 29f6bec7-9357-473e-b77e-73fb643c213d · outbound

This paper cites Figstep: Jailbreaking large vision-language models via typographic visual prompts, 2025.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM Figstep: Jailbreaking large vision-language models via typographic visual prompts, 2025

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:08:15.611989Z

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 6f009ae5-4aed-49c8-81e7-059ddedc41cd · outbound

This paper cites Kwok, and Yu Zhang.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM Kwok, and Yu Zhang

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:08:15.564633Z

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 4c306b2b-0353-4974-bc45-3cfc213e2d8c · outbound

This paper cites The llama 3 herd of models, 2024.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM The llama 3 herd of models, 2024

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:08:15.514951Z

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 cd236861-ab83-41f5-b7c9-7d6dc4e51e35 · outbound

This paper cites Minillm: Knowledge distillation of large language models, 2024.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM Minillm: Knowledge distillation of large language models, 2024

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:08:15.478924Z

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 5da337ee-3c4b-4ecf-9e24-c3550b3b57f1 · outbound

This paper cites Hod: New harmful object detection bench- marks for robust surveillance.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM Hod: New harmful object detection bench- marks for robust surveillance

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:08:15.447088Z

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 5ca6a6b8-5bcc-41f9-8cd9-cd37f023fa1a · outbound

This paper cites Tit-for-tat: Safeguarding large vision-language models against jailbreak attacks via adversarial defense, 2025.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM Tit-for-tat: Safeguarding large vision-language models against jailbreak attacks via adversarial defense, 2025

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:08:15.404207Z

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 82d02209-c09d-4a5a-8fb7-3b6aa91ff044 · outbound

This paper cites Distilling the Knowledge in a Neural Network.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM Distilling the Knowledge in a Neural Network

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T13:08:09.558348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cfd07e9-3a9d-49cf-92b7-2b773eb2f09d · outbound

This paper cites Learning multiple layers of features from tiny images.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM Learning multiple layers of features from tiny images

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T13:08:09.713335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a8f6234-e0a8-4430-82e7-ca8bf4d5aa62 · outbound

This paper cites How does vision-language adaptation impact the safety of vision language models? In The Thirteenth International Conference on Learning Representations , 2025.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM How does vision-language adaptation impact the safety of vision language models? In The Thirteenth International Conference on Learning Representations , 2025

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:08:15.343970Z

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 3b407513-0664-45b2-a636-cfe885dd8e0f · outbound

This paper cites The power of scale for parameter-efficient prompt tuning, 2021.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM The power of scale for parameter-efficient prompt tuning, 2021

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T13:08:09.990842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e2c534b-5423-4894-9d18-ecd049330485 · outbound

This paper cites Safety layers in aligned large language models: The key to LLM security.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM Safety layers in aligned large language models: The key to LLM security

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:08:15.276560Z

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 3a7b1f9e-11a3-48a7-b605-40a8882b7f89 · outbound

This paper cites Improved baselines with visual instruction tuning, 2024.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM Improved baselines with visual instruction tuning, 2024

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:08:15.223607Z

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 5f894fe9-b69e-4408-9a96-43d0a5efa368 · outbound

This paper cites Visual instruction tuning, 2023.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM Visual instruction tuning, 2023

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T13:08:10.434724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70aac814-c1a7-4aee-9e10-55cf9f793213 · outbound

This paper cites Query-relevant images jailbreak large multi-modal models, 2023.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM Query-relevant images jailbreak large multi-modal models, 2023

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:08:15.136590Z

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 6496eb7c-0bfd-4701-a4e2-d5c236b491f4 · outbound

This paper cites LLaV A-1.5-7B-HF: A hugging face implementation of llava-1.5, 2023.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM LLaV A-1.5-7B-HF: A hugging face implementation of llava-1.5, 2023

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:08:15.096758Z

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 b122cbaf-335a-4c4d-a187-8921207f7443 · outbound

This paper cites Teaching Small Language Models to Reason.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM Teaching Small Language Models to Reason

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T13:08:10.816109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b49f981-2b79-40a5-9653-303d7eac9bbc · outbound

This paper cites Llama-3.1-8b-instruct.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM Llama-3.1-8b-instruct

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:08:15.061543Z

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 d20209e9-fe38-432a-9f4e-512a34e25187 · outbound

This paper cites Llama-3.2-11b-vision.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM Llama-3.2-11b-vision

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:08:15.011634Z

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 e4e6040b-5faf-423c-b10d-b64d1f3a369d · outbound

This paper cites Mllm-protector: Ensuring mllm’s safety without hurting performance, 2024.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM Mllm-protector: Ensuring mllm’s safety without hurting performance, 2024

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:08:14.979492Z

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 adbe6d75-52a0-43c2-bda7-f7c45df8c2e7 · outbound

This paper cites On the adversarial robustness of multi-modal founda- tion models, 2023.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM On the adversarial robustness of multi-modal founda- tion models, 2023

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:08:14.935397Z

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 ae78b573-875b-46df-9dfe-fef82f42e37e · outbound

This paper cites Hashimoto.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM Hashimoto

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T13:08:11.602594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4822526-2719-424d-9270-b19f593632e7 · outbound

This paper cites Enhancing visual- language modality alignment in large vision language models via self-improvement, 2025.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM Enhancing visual- language modality alignment in large vision language models via self-improvement, 2025

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:08:14.855388Z

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 8ce74b3c-a356-42ef-b44d-4c30712b93f9 · outbound

This paper cites Adashield: Safeguarding multimodal large language models from structure-based attack via adaptive shield prompting, 2024.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM Adashield: Safeguarding multimodal large language models from structure-based attack via adaptive shield prompting, 2024

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:08:14.709567Z

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 7202e27e-0e35-49fe-ae72-7dd44a84419d · outbound

This paper cites Break the visual perception: Adversarial attacks targeting encoded visual tokens of large vision-language models, 2024.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM Break the visual perception: Adversarial attacks targeting encoded visual tokens of large vision-language models, 2024

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:08:14.537513Z

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 6062bb48-0470-4ac2-a38a-8b50b33ebd12 · outbound

This paper cites Tracking the copyright of large vision- language models through parameter learning adversarial images, 2025.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM Tracking the copyright of large vision- language models through parameter learning adversarial images, 2025

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:08:14.367214Z

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 84638ac2-ac35-4fbb-a7d6-3be4b18fac92 · outbound

This paper cites Cross-modal safety mechanism transfer in large vision-language models.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM Cross-modal safety mechanism transfer in large vision-language models

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:08:14.169471Z

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 f865ba14-4061-4fbc-8b6b-6962cc47e4e7 · outbound

This paper cites Jailbreak vision language models via bi-modal adversarial prompt, 2024.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM Jailbreak vision language models via bi-modal adversarial prompt, 2024

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T13:08:12.327395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3edd9714-00d1-4dfb-8e71-886cf0655dbe · outbound

This paper cites Mm-vet: Evaluating large multimodal models for integrated capabilities.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM Mm-vet: Evaluating large multimodal models for integrated capabilities

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:08:13.944111Z

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 5687ac9e-8fe8-4b9b-b862-b0331c550fe4 · outbound

This paper cites Spa-vl: A comprehensive safety preference alignment dataset for vision language model, 2025.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM Spa-vl: A comprehensive safety preference alignment dataset for vision language model, 2025

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:08:13.723508Z

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 9076cfd6-99a8-4cf9-90f9-fde995bfeafe · outbound

This paper cites Spot risks before speaking! unraveling safety attention heads in large vision-language models, 2025.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM Spot risks before speaking! unraveling safety attention heads in large vision-language models, 2025

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:08:13.441026Z

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 6f2ef598-1eb0-4c9f-9549-961c4b254f65 · outbound

This paper cites Safety fine-tuning at (almost) no cost: A baseline for vision large language models, 2024.

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM Safety fine-tuning at (almost) no cost: A baseline for vision large language models, 2024

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:08:13.261051Z

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 49c672e4-141b-47b7-a04c-c29148d1fdd9 · inbound

AttenTrack: Mobile User Attention Awareness Based on Context and External Distractions cites this paper.

AttenTrack: Mobile User Attention Awareness Based on Context and External Distractions Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-08-05T12:39:34.200846Z

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.