Pith. sign in

Paper Citation Record · LEDGER

Manipulating Multimodal Agents via Cross-Modal Prompt Injection

As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 10 inbound Pith citation observations for arXiv:2504.14348.

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

pith.paper-citation-record.v1
2504.14348 v4

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 10 of 10 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+00:00

measured 10 of 10 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:02:03.866331Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-18T08:16:06.487287Z

Reference resolution

0 of 0 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved0
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation fa30f3e3-9f77-4155-84c1-e2aca42e085f · inbound

PRJ: Perception-Retrieval-Judgement for Generated Images cites this paper.

PRJ: Perception-Retrieval-Judgement for Generated Images Manipulating Multimodal Agents via Cross-Modal Prompt Injection

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-07T11:02:03.866331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:02:03.866331Z digest=sha256:5780d3ef27bfe534fe212e2cf9da4f5c5f9cb096161fe0d93b3839dc39e80f09

Observation 2a247095-3659-4852-b88a-22fed94a42b8 · inbound

Prompt Injection 2.0: Hybrid AI Threats cites this paper.

Prompt Injection 2.0: Hybrid AI Threats Manipulating Multimodal Agents via Cross-Modal Prompt Injection

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-06T16:34:04.952025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:34:04.952025Z digest=sha256:f944a9bdfaf2016e2cf802213d1286a136623e3530f6f800fc603135a45848ab

Observation 47fbc2ab-ed6f-472e-9737-6e132ed1068d · inbound

Multimodal Fine-grained Reasoning for Post Quality Evaluation cites this paper.

Multimodal Fine-grained Reasoning for Post Quality Evaluation Manipulating Multimodal Agents via Cross-Modal Prompt Injection

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-06T15:42:37.809088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T15:42:37.809088Z digest=sha256:b38488d73771a38c00011137e773bd92341b01259926db06408c796068e32cd0

Observation 985a0ac5-07aa-41fc-9303-ff35510a7f03 · inbound

Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects cites this paper.

Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects Manipulating Multimodal Agents via Cross-Modal Prompt Injection

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-06T12:52:01.473903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T12:52:01.473903Z digest=sha256:79cb58c72d6100b7057ef419bceb5f44afc882b4f732d5c7963e0c1f257db977

Observation 6c994ed2-b110-4413-872c-248d9ce14731 · inbound

Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks? cites this paper.

Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks? Manipulating Multimodal Agents via Cross-Modal Prompt Injection

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-04T23:49:33.164739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T23:49:33.164739Z digest=sha256:df374a9bb3f7fe87ee125c690de842ff2c0c6a7261b543df49683608729914c5

Observation 17fd2714-c315-4cf1-b6a5-a2de4ea56449 · inbound

SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents cites this paper.

SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Manipulating Multimodal Agents via Cross-Modal Prompt Injection

Reference 41

Resolution
verified exact
arxiv_id, observed 2026-05-18T08:16:06.490295Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-05-18T08:14:51.102085Z digest=sha256:f4fd36f3120c76dfe90197f251f139681b60ee8a0dfa0be0dcbc5e360f34be81

Observation b3090f75-8209-436a-ad65-5470229fabba · inbound

Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges cites this paper.

Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges Manipulating Multimodal Agents via Cross-Modal Prompt Injection

Reference 79

Resolution
verified exact
arxiv_id, observed 2026-05-18T03:42:22.021033Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-05-18T03:42:10.703369Z digest=sha256:974d9353748daceaea82cbd8c94bb4d824faf1599b9ad3270142bff652a1ba4b

Observation e87d6b9c-7ad8-445a-9149-17b16da3537b · inbound

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs cites this paper.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs Manipulating Multimodal Agents via Cross-Modal Prompt Injection

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-02T08:55:49.141115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T08:55:49.141115Z digest=sha256:1f9235638ea901f9c0ca9dce3866484c6ede31aaccc3bc737f9f5eef102a1810

Observation d655a8ad-6a58-4b7d-98d6-ddb8635af7b3 · inbound

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs cites this paper.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs Manipulating Multimodal Agents via Cross-Modal Prompt Injection

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-04T04:34:33.210622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:34:33.210622Z digest=sha256:fd761dc3fda219441ed47d0d5a5b871b90306147501d74c66276b9c1957beb60

Observation ba1048b2-f49c-4347-bf86-b6ea76ff35b8 · inbound

Agent Security Needs Redefinition through a Holistic Framework cites this paper.

Agent Security Needs Redefinition through a Holistic Framework Manipulating Multimodal Agents via Cross-Modal Prompt Injection

Reference 294

Resolution
unresolved
no resolver link, observed 2026-08-01T06:04:46.726071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T06:04:46.726071Z digest=sha256:b72e70c836227e54b6f23dad9908786647d6de00fd58ba648b3dc377fc80139d