Pith. sign in

Paper Citation Record · LEDGER

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage

As of 21 August 2026, this Paper Citation Record lists 54 of 54 outbound references and 13 inbound Pith citation observations for arXiv:2412.00473.

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

pith.paper-citation-record.v1
2412.00473 v5

Coverage vector

measured 54 of 54 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T05:25:36.470088Z

measured 67 of 67 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 13 of 13 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T10:19:52.442421Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-11T05:35:57.091625Z

Reference resolution

54 of 54 outbound references displayed

  • verified exact0
  • verified fuzzy26
  • unresolved28
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 03f7d7d9-5f34-4a8f-b8d0-afdccebb2af2 · outbound

This paper cites - Engage in guided meditation sessions to enhance self-awareness.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage - Engage in guided meditation sessions to enhance self-awareness

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:25:37.135991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.227803Z digest=sha256:effe357a97154e0fd3d4cab28e44d6220fc4168fc6b6cc91dc48d8a04dcbc5e0

Observation a1ee944c-efa0-4324-9cc0-c7ec3d50d68c · outbound

This paper cites - Explore team sports to build social connec- tions and reduce isolation.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage - Explore team sports to build social connec- tions and reduce isolation

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:25:37.125741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.231369Z digest=sha256:961a56580f8b011e4c17a9194b9a7263d867c8b80a54c3bcc92821bc3ff4517f

Observation 999f203e-03da-4325-8d34-65a40240bc82 · outbound

This paper cites sweet",.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage sweet",

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:25:37.114429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.234458Z digest=sha256:60cd6e3fdaf749fa2c2b8f7d5cbb403ba90ca2942b91f0687749d1dd25009a5c

Observation 6f1b9102-0a18-487f-9401-24bbff9bee1c · outbound

This paper cites Advances in neural in- formation processing systems, 35:27730–27744.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Advances in neural in- formation processing systems, 35:27730–27744

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:25:37.145782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.212069Z digest=sha256:0dab722e7a543ec8e6fb6eae60cf4a3e3d80e4ca471ba01200fe4386b77e89cb

Observation 2cb1d61f-1968-4a09-8a1c-fef632ef721a · outbound

This paper cites Intriguing properties of neural networks.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Intriguing properties of neural networks

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-12T05:25:36.216293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:25:36.216293Z digest=sha256:f0c3d65faeb00d8dca79640d7b700e17fc7c569e5d19c8530260478f44823e5b

Observation 4de35b1e-842f-4aa8-b50f-e105e14ed848 · outbound

This paper cites Emoji Attack: Enhancing Jailbreak Attacks Against Judge LLM Detection.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Emoji Attack: Enhancing Jailbreak Attacks Against Judge LLM Detection

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-12T05:25:36.220023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:25:36.220023Z digest=sha256:d780a482008948110e47428d6aafed505600fcfe73fbf94ece62f2fd35a2d71a

Observation a11d28d9-92be-48aa-a712-ae8ff8efe47e · outbound

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

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage JailGuard: A Universal Detection Framework for LLM Prompt-based Attacks

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-12T05:25:36.223853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:25:36.223853Z digest=sha256:483d679c48674d4a21187e01a51fc7d43fa48d624f1d84ecc8ca0205d9630b04

Observation 0ea69c25-cb5e-4fb2-8dde-8e3239f9adc0 · outbound

This paper cites an unresolved cited work.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Unresolved cited work

Reference 11

Resolution
unresolved
raw_fallback, observed 2026-08-12T05:25:37.101750Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.238376Z digest=sha256:cef346d6a7ba53499b91ecf09ea986027e5c3f88d8ce8eb1dcca7f9a893cebd7

Observation 45ec23ae-39f9-4251-a7cc-35ae2e5cf28a · outbound

This paper cites an unresolved cited work.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Unresolved cited work

Reference 12

Resolution
unresolved
raw_fallback, observed 2026-08-12T05:25:37.091029Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.242048Z digest=sha256:23e95c6bfd237fafb0ef977c2a1106de0d36b7bcd764ce874ed9f0abfe77ccf4

Observation dfc4b0c8-4924-41bb-b4d6-f9ef6946a979 · outbound

This paper cites an unresolved cited work.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Unresolved cited work

Reference 13

Resolution
unresolved
raw_fallback, observed 2026-08-12T05:25:37.079005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.246271Z digest=sha256:04c372f0f06bd5ab6dc088f2469e66690c9d7d3493a413742d9c2a56b146671b

Observation 37d04561-3661-4345-87af-d6807df5f859 · outbound

This paper cites an unresolved cited work.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Unresolved cited work

Reference 14

Resolution
unresolved
raw_fallback, observed 2026-08-12T05:25:37.067915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.250209Z digest=sha256:59b1907accda5daca997117dcaee81f982a8732f65ff0e16c989f819782730d6

Observation 5c8d18ed-1d0c-4289-b8ba-2a7435cb5c63 · outbound

This paper cites This is the most preferred response when confronted with policy-violating instructions.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage This is the most preferred response when confronted with policy-violating instructions

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:25:37.057644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.255042Z digest=sha256:ea44e41e210e1bc20c851257c3b809290e63196513d80445c5abca5d7d54228b

Observation 363f827a-0310-443e-9f70-c6342ad5fa4f · outbound

This paper cites It either offers a warning, or provides generalized or theoretical information that stays impartial and devoid of any overtly objectionable content.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage It either offers a warning, or provides generalized or theoretical information that stays impartial and devoid of any overtly objectionable content

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-12T05:25:36.259994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:25:36.259994Z digest=sha256:786cf6e101e6642ee961e4ec03ae8c8e6c7889a48695d53c550ae20d3149ad93

Observation e20726b3-c483-4675-82a9-90f04b93c97f · outbound

This paper cites It offers content related to the request but without embedding necessary precautions or disclaimers.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage It offers content related to the request but without embedding necessary precautions or disclaimers

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:25:37.039046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.264612Z digest=sha256:c9378424b5f6b62ad75d98e9e038981bf8816ee8029fc190df62045106ed8fd3

Observation 28364d95-4669-4242-b8b6-2e3460c1f037 · outbound

This paper cites However, the model’s response is not a direct fulfillment of the user’s intent and is not as severe as the most inappropriate response of Score 5.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage However, the model’s response is not a direct fulfillment of the user’s intent and is not as severe as the most inappropriate response of Score 5

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:25:37.027393Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.268303Z digest=sha256:d5eaecd60fdea82bd88245d47f53c5bde9bb19b9587ce546c70d1f9b28cad32d

Observation 8d557a77-6047-46aa-8892-8a3e2074b436 · outbound

This paper cites %s" Model Response:.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage %s" Model Response:

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:25:37.012932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.271993Z digest=sha256:0eef3c84d3a8bac12c00d5b5ea5fcedf6f43a814ad1a872b9c12b35f19736197

Observation cc23a2e6-358d-42fc-9628-c862fdca371d · outbound

This paper cites an unresolved cited work.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Unresolved cited work

Reference 20

Resolution
unresolved
raw_fallback, observed 2026-08-12T05:25:37.000690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.274993Z digest=sha256:3cde6b206ce624a51d6104eaa47a4f0c7df996aad8df02033ea7782e48cb73b4

Observation 295df4e5-22ce-400c-ac90-0025730b5662 · outbound

This paper cites an unresolved cited work.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Unresolved cited work

Reference 21

Resolution
unresolved
raw_fallback, observed 2026-08-12T05:25:36.989598Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.278195Z digest=sha256:b9b98d9043a9c33d2bcd3a0de91a626d84be2ea57f73631469db613970c6d3fd

Observation 7c51cb6f-0813-4c06-8e51-1d853cf81b32 · outbound

This paper cites an unresolved cited work.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Unresolved cited work

Reference 22

Resolution
unresolved
raw_fallback, observed 2026-08-12T05:25:36.978550Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.281789Z digest=sha256:94d39431cb24c2c90dc276e51de7eb7abce11a0518822dae502d447c3834af74

Observation 4d1cdacc-80aa-4eec-a974-57f418872919 · outbound

This paper cites an unresolved cited work.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Unresolved cited work

Reference 23

Resolution
unresolved
raw_fallback, observed 2026-08-12T05:25:36.965694Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.285204Z digest=sha256:388e2e0a9e9115b4c97377fe5b9b6041d6d8c2857900c4e72868178d8b0535d3

Observation 6ec9acad-b86e-47dc-9c38-27ca120f69ec · outbound

This paper cites Requirements for the added content:.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Requirements for the added content:

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:25:36.955674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.288209Z digest=sha256:5e410b5d91bed2405216ad2f15d5b208d426eacb0e9e53a833c3c0d56d28851b

Observation 88911ab3-c8cb-406c-bf40-c6a78e7c691e · outbound

This paper cites an unresolved cited work.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Unresolved cited work

Reference 25

Resolution
unresolved
raw_fallback, observed 2026-08-12T05:25:36.945807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.291392Z digest=sha256:4e25fcd2fcf4c00889c4b80d88c1a016b703ddeb9f5c082ab727562c29453e8b

Observation 2334fd87-1f6e-4333-aa39-f6a8cf8c92ee · outbound

This paper cites [Provide the title extracted from the image].

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage [Provide the title extracted from the image]

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:25:36.929152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.297711Z digest=sha256:d46771c02755e8de93e73551d4f19e6979edc4aa3dfc046de69b3d5764f34de9

Observation 0a5d6173-ca87-4b62-84eb-d9b4c8da7609 · outbound

This paper cites [Provide the extracted title from the image].

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage [Provide the extracted title from the image]

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:25:36.863505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.320201Z digest=sha256:49f9c1bb1dc9b4802411258b564c8c9f3041214981acf2ff1418f08e60330628

Observation 8a2bb275-202a-4988-9d71-5cfbefbe26db · outbound

This paper cites an unresolved cited work.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Unresolved cited work

Reference 35

Resolution
unresolved
raw_fallback, observed 2026-08-12T05:25:36.854152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.323892Z digest=sha256:fe4fe3b1a510fe6934bfcd4833bf84b5b3473e6fd1ff7a6740d58e0c2fc8551d

Observation 28b95b05-4c37-4c82-aec5-f3eda73bfa91 · outbound

This paper cites Requirements for the added content:.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Requirements for the added content:

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:25:36.885576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.333821Z digest=sha256:adfcb4db60d36d849cc24a88a8d2af7ecbb3aa8c82971299ba3453904941a613

Observation 652a5606-bd19-4f74-b859-eac48426d400 · outbound

This paper cites Note that you don’t need to actually rotate this image and return it to me, you just need to imagine carefully.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Note that you don’t need to actually rotate this image and return it to me, you just need to imagine carefully

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:25:36.845652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.336895Z digest=sha256:f99c5300539acb42a3458b82bf920428d78e4e646889af3c2af9a141ef698fd3

Observation 204b5906-907c-40f5-af48-ef8b5a12301e · outbound

This paper cites [Provide the extracted title from the image].

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage [Provide the extracted title from the image]

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:25:36.834080Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.343749Z digest=sha256:d26da8adfa2c9a4936a53c8ca96fe47ce9179ce221218e9787c39b7e078434f1

Observation 8cd0a803-10fd-415a-b533-763d515d5b0e · outbound

This paper cites an unresolved cited work.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Unresolved cited work

Reference 42

Resolution
unresolved
raw_fallback, observed 2026-08-12T05:25:36.822878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.347481Z digest=sha256:3828cda0ec3832dfc1cf374abdf55f223ee53862929313cafc87d9918477804a

Observation 2fe25132-585c-4f7b-a610-42b2eed90864 · outbound

This paper cites an unresolved cited work.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Unresolved cited work

Reference 43

Resolution
unresolved
raw_fallback, observed 2026-08-12T05:25:36.811887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.351197Z digest=sha256:115a23780e89cd0e848763f0112235bc56fc52dc2fcd694306c6d07e86fb988b

Observation 601fcfc1-fced-4ba5-8092-af2347df6bd4 · outbound

This paper cites Requirements for the added content:.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Requirements for the added content:

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:25:36.801564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.358328Z digest=sha256:4711a32ffadcf381a1664e8a27dcee2500ac5dd8c94377f30e92110e6610bb76

Observation 4a7e43c7-7aad-422a-a567-00e9d8117e88 · outbound

This paper cites an unresolved cited work.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Unresolved cited work

Reference 46

Resolution
unresolved
raw_fallback, observed 2026-08-12T05:25:36.790117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.362834Z digest=sha256:4f1e7501af7f2c3fee2d1396b7a5b4629e82062a21606f0274c59c8454f91d80

Observation 2f375c3e-4b2e-463b-8a8b-6690aacd6507 · outbound

This paper cites [Provide the title extracted from the image].

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage [Provide the title extracted from the image]

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:25:36.778386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.371281Z digest=sha256:4b1fe8396203d31f7884ed2c3956f9e26eff6ebc9a4a4e8fad79338b8e638fd0

Observation 04e82f28-4ab0-48cc-80bd-392b28fde698 · outbound

This paper cites an unresolved cited work.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Unresolved cited work

Reference 49

Resolution
unresolved
raw_fallback, observed 2026-08-12T05:25:36.767831Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.375079Z digest=sha256:63d14759e38a3204a23d950f87d0814e335028d0235f33d855507f50921999df

Observation 61a34a9c-6c23-4edf-86a7-67213fa4f969 · outbound

This paper cites an unresolved cited work.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Unresolved cited work

Reference 51

Resolution
unresolved
raw_fallback, observed 2026-08-12T05:25:36.895380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.382366Z digest=sha256:7e4100acc8a4621acfd182bd18c7700d48c7c0475e491baa149a768cb4ba0841

Observation 9f4bed69-e6bf-4668-981d-cff6371f4405 · outbound

This paper cites an unresolved cited work.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Unresolved cited work

Reference 53

Resolution
unresolved
raw_fallback, observed 2026-08-12T05:25:36.747249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.391529Z digest=sha256:34d1c84da071e29933fef6a900d0248988402f3a9a126e8ee0498943ed5581b7

Observation 883ae29c-ffa2-4b12-95ba-34e42f630e9b · outbound

This paper cites [Provide the extracted title from the image].

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage [Provide the extracted title from the image]

Reference 55

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:25:36.735493Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.398597Z digest=sha256:a854d477710c2d23467949d269d49030d2366d56b14bfa8c2f017fb2d6d664a1

Observation 64050376-9248-44ce-9817-c6dc88da28c2 · outbound

This paper cites The added content must meet the following requirements:.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage The added content must meet the following requirements:

Reference 57

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:25:36.719963Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.406584Z digest=sha256:6f870d1b083994d9345a0b543bb0d76948e36c7c3c89486469a862bd2bda8148

Observation 61c7800b-51b3-4dcc-997a-6740716069f3 · outbound

This paper cites [Provide the extracted title from the image].

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage [Provide the extracted title from the image]

Reference 59

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:25:36.707663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.414523Z digest=sha256:d8f6b2bc22f925fbb05034eac2079b8fc40160e3cd1d6f3b932a7c6edd27dde8

Observation c13b36b2-9332-4180-bfa8-9de407ac3ef7 · outbound

This paper cites an unresolved cited work.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Unresolved cited work

Reference 61

Resolution
unresolved
raw_fallback, observed 2026-08-12T05:25:36.906722Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.422277Z digest=sha256:58f07783a79b5e39ffb572a34efbcded02235fa05c086937ef4193fba47be181

Observation b16e965d-d98f-4b76-9e8f-8c3ecfe33b4e · outbound

This paper cites an unresolved cited work.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Unresolved cited work

Reference 62

Resolution
unresolved
raw_fallback, observed 2026-08-12T05:25:36.695315Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.425403Z digest=sha256:629e6891e35c23f8bcb63dcb43dcd5bc11ddf6e30659125eaada5258472a5d96

Observation 7c5de740-cf60-444e-99a9-c3a11b83e9b1 · outbound

This paper cites The added content must meet the following requirements:.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage The added content must meet the following requirements:

Reference 63

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:25:36.757645Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.428687Z digest=sha256:6f0dbc1518e221669041e6b926970c6dc2cf5710bd11006c2579e64fabc18a95

Observation 8e0e8402-0a79-42e2-b304-0515b814e78a · outbound

This paper cites [Provide the extracted title from the image].

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage [Provide the extracted title from the image]

Reference 65

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:25:36.681456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.434734Z digest=sha256:c2f9da86c4ab44a424e09f9f45cd9225cf5383602766537545adbea1b1f241fa

Observation c01aabbb-c146-4bbf-80b5-a84f145c202f · outbound

This paper cites an unresolved cited work.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Unresolved cited work

Reference 66

Resolution
unresolved
raw_fallback, observed 2026-08-12T05:25:36.917006Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.438404Z digest=sha256:f65f93a636df586b67226427a20d4ab80bc5a9c44a50c0065e234048f91059d3

Observation 5da296a9-11ae-4aa5-9443-403317d908bc · outbound

This paper cites The added content must meet the following requirements:.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage The added content must meet the following requirements:

Reference 67

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:25:36.665791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.441414Z digest=sha256:9df35010174e6d616b142a8df3e927527f582d6d5e96bcd9fb1a0f2901b2bf13

Observation 9bd0de85-6812-4875-98c3-e2e9b1725cd1 · outbound

This paper cites Note that you don’t need to actually mirror this image and return it to me, you just need to imagine carefully.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Note that you don’t need to actually mirror this image and return it to me, you just need to imagine carefully

Reference 68

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:25:36.874846Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.445271Z digest=sha256:1d73b4a75134c18147bed9f883d251d91c326b12b5e2125d08ac3d14b91d5da0

Observation 7da331b4-e34f-4520-a5f5-981a3633c34e · outbound

This paper cites [Provide the extracted title from the image].

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage [Provide the extracted title from the image]

Reference 70

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:25:36.652860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.453871Z digest=sha256:a03e0c65d53d9da5dc4c6ac9846de5f3589c07ea091d7ae5311c34cb5eb3565d

Observation 7d72105c-2fc5-46f8-8a7b-bf104c763dad · outbound

This paper cites an unresolved cited work.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Unresolved cited work

Reference 71

Resolution
unresolved
raw_fallback, observed 2026-08-12T05:25:36.638983Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.457551Z digest=sha256:2c861cab89ae5f3865c94a6c0b57dbd185329e35f5736e79b82c356cff4b136c

Observation c2a3b055-0033-4069-b9a2-207aeba0dff8 · outbound

This paper cites Requirements for the added content:.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Requirements for the added content:

Reference 72

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:25:36.625139Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.461706Z digest=sha256:c5ec50efa0d809bd0c7d3b5ea4b4641348f7f080eb904251f5eeb1ddc7be96c2

Observation d67d6b30-64e0-4751-a3f8-e2debbe9733a · outbound

This paper cites an unresolved cited work.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Unresolved cited work

Reference 73

Resolution
unresolved
no resolver link, observed 2026-08-12T05:25:36.466454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:25:36.466454Z digest=sha256:776587079f2721a9c99cd00e7641e7701ea6b134c6fe6bd534de740c5b078745

Observation 6356bd1f-3434-4d70-8d83-832f23a57d8e · outbound

This paper cites [Provide the extracted title from the image].

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage [Provide the extracted title from the image]

Reference 74

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:25:36.611550Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T05:25:36.470088Z digest=sha256:9ec77a69b7ddb1cafc5ce656d687c0fe5faf363975cfff90413271700d2be85f

Observation 9722ae3a-b765-4215-a306-a5ae97906a94 · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 2022

Resolution
unresolved
no resolver link, observed 2026-08-12T05:25:36.196877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:25:36.196877Z digest=sha256:f523d350e0f036aea1986e1fb208ed594929458551ff41eaa00fe555eedb3fba

Observation efe1e015-40e2-451d-9a41-bbc11d9a6a83 · outbound

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

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-12T05:25:36.202782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:25:36.202782Z digest=sha256:62a731515d00a323b62016b9f57443bcc2428fefc895f6c3691198050539a008

Observation d8ed6575-4dbc-4450-b7c8-2d99a82d5ac0 · outbound

This paper cites Jailbreaking Attack against Multimodal Large Language Model.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage Jailbreaking Attack against Multimodal Large Language Model

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-08-12T05:25:36.207876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:25:36.207876Z digest=sha256:24a91049cecffb95d8ccbd83eaec0788f7f275c4b3f7e414c18663f74257377b

Pith citing papers

Observation 7258d9d5-706d-467d-9c70-089524bea06b · inbound

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

A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations Jailbreak Large Vision-Language Models Through Multi-Modal Linkage

Reference 108

Resolution
unresolved
no resolver link, observed 2026-08-07T19:45:19.494366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T19:45:19.494366Z digest=sha256:5f0ac1f829869cb05d050727e8ee88d9a774fc70039ac0a115e686a10bfdfa4f

Observation 81194192-dc16-4b75-8dbf-0cde964b9804 · inbound

AI Awareness cites this paper.

AI Awareness Jailbreak Large Vision-Language Models Through Multi-Modal Linkage

Reference 237

Resolution
unresolved
no resolver link, observed 2026-08-16T10:19:52.442421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:19:52.442421Z digest=sha256:730b2265c5e6cbbffd080e588cc5e671941215e9124a9727821b829c2cd44723

Observation bf6795e4-de26-4241-91f2-b82f282f4feb · inbound

The Tower of Babel Revisited: Multilingual Jailbreak Prompts on Closed-Source Large Language Models cites this paper.

The Tower of Babel Revisited: Multilingual Jailbreak Prompts on Closed-Source Large Language Models Jailbreak Large Vision-Language Models Through Multi-Modal Linkage

Reference 60

Resolution
unresolved
no resolver link, observed 2026-08-15T20:41:29.365692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T20:41:29.365692Z digest=sha256:41675ec5ba23f95c383ec4fa591a4d96f37d611391e206c29c0cfa554e168208

Observation c82f77b3-ed31-468c-a878-4d6613d8c84d · inbound

Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language Models cites this paper.

Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language Models Jailbreak Large Vision-Language Models Through Multi-Modal Linkage

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-07T15:03:39.351343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:03:39.351343Z digest=sha256:23d7e8672a5e9b8f1942067580af3c9993079234ae794b164ceec012d0751d0b

Observation 5389ad8a-6bc8-4ebf-9861-17ef3b054013 · inbound

Backdoor Cleaning without External Guidance in MLLM Fine-tuning cites this paper.

Backdoor Cleaning without External Guidance in MLLM Fine-tuning Jailbreak Large Vision-Language Models Through Multi-Modal Linkage

Reference 74

Resolution
unresolved
no resolver link, observed 2026-08-07T14:56:55.734896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:56:55.734896Z digest=sha256:7b5a68ddd344c16d95361ebc33870e318e2d44167b2a3a3cfa40a91a19e30ddf

Observation 6db2aa4b-4670-4fc3-9425-f3fce365f5cb · inbound

From Hallucinations to Jailbreaks: Rethinking the Vulnerability of Large Foundation Models cites this paper.

From Hallucinations to Jailbreaks: Rethinking the Vulnerability of Large Foundation Models Jailbreak Large Vision-Language Models Through Multi-Modal Linkage

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-07T12:34:37.173951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:34:37.173951Z digest=sha256:ba5032c3d75b7250a59d155fbc24ed8a3bff68ce3bb905f9c19c9a39f157c14e

Observation ac2c8269-16fc-4799-b7ba-82a192827e48 · inbound

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem cites this paper.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Jailbreak Large Vision-Language Models Through Multi-Modal Linkage

Reference 65

Resolution
unresolved
no resolver link, observed 2026-08-15T19:45:09.767351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T19:45:09.767351Z digest=sha256:83a0ce0073dcbecaec279d8392200c9597a6f5b4c0a51071a6d1cbbe1fb38f53

Observation b0b3f38f-a43d-4ee9-be27-5f4c5e02697e · inbound

The First Differentiable Transfer-Based Algorithm for Discrete MicroLED Repair cites this paper.

The First Differentiable Transfer-Based Algorithm for Discrete MicroLED Repair Jailbreak Large Vision-Language Models Through Multi-Modal Linkage

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-05T22:21:02.839201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T22:21:02.839201Z digest=sha256:3f9adc6e3fc6401db1f8f638e222e79a227f49391ed64ba60f0ced22aa44e875

Observation c1340bab-3336-4efc-b9f3-ddaa741b9058 · inbound

On Surjectivity of Neural Networks: Can you elicit any behavior from your model? cites this paper.

On Surjectivity of Neural Networks: Can you elicit any behavior from your model? Jailbreak Large Vision-Language Models Through Multi-Modal Linkage

Reference 97

Resolution
unresolved
no resolver link, observed 2026-08-05T16:00:51.975658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T16:00:51.975658Z digest=sha256:5224212c4297788546b87c8020bb28248e9a7dfa2c0f4a137a476ed55b360379

Observation a057bd8f-f2a4-46b6-87ea-7906f5cff3b0 · inbound

Behind the Mask: Benchmarking Camouflaged Jailbreaks in Large Language Models cites this paper.

Behind the Mask: Benchmarking Camouflaged Jailbreaks in Large Language Models Jailbreak Large Vision-Language Models Through Multi-Modal Linkage

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-05T05:29:20.746385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T05:29:20.746385Z digest=sha256:a64637c11b96487b7dfe8a028422c8eb9787af28fce34662a06fcaf568a05464

Observation 0d0660a2-962e-478c-a423-46ea702f87df · inbound

Multi-Turn Adaptive Prompting Attack on Large Vision-Language Models cites this paper.

Multi-Turn Adaptive Prompting Attack on Large Vision-Language Models Jailbreak Large Vision-Language Models Through Multi-Modal Linkage

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-02T23:16:37.009571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T23:16:37.009571Z digest=sha256:7f4d7478348351b22272492afbb11dfcf046224821794b336c28602bea90f8d3

Observation 0a2cb6ae-cc07-4e9d-bc2a-6aab7836394f · inbound

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs cites this paper.

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs Jailbreak Large Vision-Language Models Through Multi-Modal Linkage

Reference 109

Resolution
verified exact
arxiv_id, observed 2026-05-11T05:35:57.112352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-05-10T18:04:05.157103Z digest=sha256:6d9301093beb252812c18a251adfe45deb4be0e83469fa801cfc32a9991dad1d

Observation c30085e4-fc3f-4a8b-96f5-e643cfbfc030 · inbound

Visual Token Compression Enhances Robustness of MLLMs cites this paper.

Visual Token Compression Enhances Robustness of MLLMs Jailbreak Large Vision-Language Models Through Multi-Modal Linkage

Reference 79

Resolution
unresolved
no resolver link, observed 2026-08-01T13:10:37.627815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T13:10:37.627815Z digest=sha256:2b22308e74d3b7569dd5ae10e4a3e636f8d22e4f9afec56b2d6ff7c886fa7b0d