Paper Citation Record · LEDGER

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models

As of 18 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2506.16760.

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

pith.paper-citation-record.v1
2506.16760 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T23:42:43.269669Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+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

38 of 38 outbound references displayed

verified exact0
verified fuzzy13
unresolved25
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d204f17c-1770-4b55-97e0-ac8438e63efb · outbound

This paper cites an unresolved cited work.

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T23:42:38.365135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41261ed3-e84b-4928-af26-2b0df8d2067b · outbound

This paper cites GPT-4 Technical Report.

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models GPT-4 Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T23:42:38.611607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbfa95c3-7b3a-4a3b-a2db-1260d716177a · outbound

This paper cites https://together.ai (2025), accessed: 2025- 06.

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models https://together.ai (2025), accessed: 2025- 06

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:42:49.814753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 22ca9b99-9f0f-4a3f-a0e6-42b811b09326 · outbound

This paper cites Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks.

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T23:42:38.875494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 864b1d06-e646-4b04-8962-2d50ea9004ea · outbound

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

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T23:42:38.985969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9af55388-72f1-4d6d-8645-b79be8e28636 · outbound

This paper cites an unresolved cited work.

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:42:49.563495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6bc3847a-7a3e-4c32-af17-778fd7fab464 · outbound

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

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T23:42:39.216412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58d4f8c3-ac1a-4392-9c3d-2dfed39261b3 · outbound

This paper cites In: Proceedings of the AAAI Confer- ence on Artificial Intelligence.

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models In: Proceedings of the AAAI Confer- ence on Artificial Intelligence

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:42:49.303543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7d6339da-4eb8-4313-87ea-e6e94e8870cf · outbound

This paper cites arXiv preprint arXiv:2402.10601 (2024).

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models arXiv preprint arXiv:2402.10601 (2024)

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T23:42:39.438993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c63fd57d-3bff-4954-9b0f-a10b07749024 · outbound

This paper cites GPT-4o System Card.

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models GPT-4o System Card

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T23:42:39.589878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 835a3e93-2361-4b44-b00c-33241bd8a543 · outbound

This paper cites https://pypi.org/project/easyocr/1.7.1/ (2023), accessed: 2024-02-09.

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models https://pypi.org/project/easyocr/1.7.1/ (2023), accessed: 2024-02-09

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:42:49.054821Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ff304ecb-6229-456a-9f57-fe650cf25fc4 · outbound

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

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T23:42:39.896114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 190e3b4f-485e-4189-80c1-27120b0fcbb8 · outbound

This paper cites In: International conference on machine learning.

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models In: International conference on machine learning

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:42:48.839995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b6ab3f03-9479-4fe9-a079-99a02e47787f · outbound

This paper cites In: European Conference on Computer Vision.

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models In: European Conference on Computer Vision

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:42:48.558798Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6cbea444-5a75-419d-a0aa-fce307d28d7a · outbound

This paper cites AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs.

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T23:42:40.394893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 982b7b19-af86-4167-9b65-c5b88ab5fb9e · outbound

This paper cites In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:42:48.304761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e904f8bd-0f34-42c2-893e-6422cd680200 · outbound

This paper cites In: 33rd USENIX Security Symposium (USENIX Security 24).

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models In: 33rd USENIX Security Symposium (USENIX Security 24)

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:42:48.024974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f947fcdf-6ac4-4019-b54a-c4a7f1f57347 · outbound

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

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T23:42:40.739634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79ed48ae-7ca7-4c59-b021-fe15e5a9a1cb · outbound

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

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T23:42:40.840053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68c36517-5c9c-4150-af93-e2a760df8424 · outbound

This paper cites Proceedings of Machine Learning Research235, 35181–35224 (2024).

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models Proceedings of Machine Learning Research235, 35181–35224 (2024)

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:42:47.781778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b4af6ff0-a14e-441c-983f-55d47c155843 · outbound

This paper cites Jailbreaking Attack against Multimodal Large Language Model.

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models Jailbreaking Attack against Multimodal Large Language Model

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T23:42:41.206394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2896ce1f-c4c1-4d4e-aa3f-cb99aedcc184 · outbound

This paper cites https://platform.openai.com/ docs/guides/moderation (2024), accessed: 2024-02-09.

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models https://platform.openai.com/ docs/guides/moderation (2024), accessed: 2024-02-09

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:42:47.544754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation db215771-bb22-4178-8afe-facd88371c62 · outbound

This paper cites https://openai.com/index/ gpt-4-1/ (2025), accessed: 2025-06.

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models https://openai.com/index/ gpt-4-1/ (2025), accessed: 2025-06

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:42:47.275459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6cd89896-2a5f-442b-896b-2f847f6f69fe · outbound

This paper cites In: The Twelfth International Conference on Learning Representations (2023).

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models In: The Twelfth International Conference on Learning Representations (2023)

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:42:47.048335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5ea30eb6-5d5f-4bf6-9d01-dc0b3a1c8436 · outbound

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

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T23:42:41.934834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a3a3a96-ad71-4c9d-b489-e026c2e90ac6 · outbound

This paper cites an unresolved cited work.

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:42:46.854892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 81fb3274-f7c0-480e-b65b-cb8f14eb9ac0 · outbound

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

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T23:42:42.179391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e188cac1-90db-4257-90e6-106dfa414d3e · outbound

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

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T23:42:42.384833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c05cc6b6-df0a-4b80-a1be-aba46ecb7652 · outbound

This paper cites In: Proceedings of the 32nd ACM International Conference on Multime- dia.

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models In: Proceedings of the 32nd ACM International Conference on Multime- dia

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:42:46.649677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f1443ad0-5f48-4817-8693-1e369d10af80 · outbound

This paper cites CogVLM: Visual Expert for Pretrained Language Models.

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models CogVLM: Visual Expert for Pretrained Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T23:42:42.594752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99ec7fa8-3e09-4ae9-8ff6-46491f808e1f · outbound

This paper cites Qwen2 Technical Report.

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models Qwen2 Technical Report

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T23:42:42.674859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab1fac99-7b25-45e7-aefb-79ca5e1c65eb · outbound

This paper cites A Survey on Multimodal Large Language Models.

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models A Survey on Multimodal Large Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T23:42:42.738914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation feee3bb0-1f51-4cd0-a73d-c45e8e78c78d · outbound

This paper cites Low-Resource Languages Jailbreak GPT-4.

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models Low-Resource Languages Jailbreak GPT-4

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T23:42:42.798103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 820d8f86-6714-42f3-8fd9-c2763326728f · outbound

This paper cites GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher.

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T23:42:42.971360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad1bbe46-1f26-4f24-96cd-381d9f5f9ab1 · outbound

This paper cites In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguis- tics (V olume 1: Long Papers).

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguis- tics (V olume 1: Long Papers)

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:42:46.457553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8282f364-aaa8-42d3-86a1-11243466b13c · outbound

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

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T23:42:43.107250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f732304b-780e-4793-b2b8-d551cfef81b4 · outbound

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

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T23:42:43.172464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19f92926-8a56-4b08-abb8-150322b8b4cb · outbound

This paper cites an unresolved cited work.

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models Unresolved cited work

Reference 39

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:42:46.123015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Pith citing papers

No inbound Pith citation observations are available.