Paper Citation Record · LEDGER

Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs

As of 18 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 1 inbound Pith citation observation for arXiv:2509.05883.

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

pith.paper-citation-record.v1
2509.05883 v1

Coverage vector

measured 18 of 18 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T04:56:25.081296Z

measured 19 of 19 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T14:21:42.687544Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-15T18:16:14.067578Z

Reference resolution

18 of 18 outbound references displayed

verified exact2
verified fuzzy11
unresolved5
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 021c3624-6ddc-4205-9978-11efa5b050de · outbound

This paper cites A novel system for strengthening security in large language models,.

Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs A novel system for strengthening security in large language models,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:56:25.645090Z

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 a35ce5c2-ac87-4d6c-8749-8ec85a4dc0c4 · outbound

This paper cites System Prompt Poisoning: Per- sistent Attacks on Large Language Models Beyond User Injection,.

Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs System Prompt Poisoning: Per- sistent Attacks on Large Language Models Beyond User Injection,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T04:56:24.983039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ac67f20-25c4-4545-b610-39e291267631 · outbound

This paper cites Prompt Injection attack against LLM-integrated Applications.

Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs Prompt Injection attack against LLM-integrated Applications

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T04:56:24.995208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08698c30-d76a-404a-bd0a-4f6affba6a45 · outbound

This paper cites Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems.

Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T04:56:25.012214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 140df5bd-cf66-46a1-a094-06f328777c72 · outbound

This paper cites PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models.

Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-08-05T04:56:25.195689Z

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 320562d3-da33-4971-873a-9a2b35969801 · outbound

This paper cites Goal-guided Generative Prompt Injection Attack on Large Language Models.

Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs Goal-guided Generative Prompt Injection Attack on Large Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T04:56:25.024461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f9248a0-795d-4888-b8a5-316d398ac9ef · outbound

This paper cites Systematically Analyzing Prompt Injection Vulnerabilities in Diverse LLM Architectures.

Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs Systematically Analyzing Prompt Injection Vulnerabilities in Diverse LLM Architectures

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-08-05T04:56:25.144199Z

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 156ceebf-f4a9-419d-bae5-490566a580dd · outbound

This paper cites Visual Prompt Injection Attacks in Modern Large Language Models,.

Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs Visual Prompt Injection Attacks in Modern Large Language Models,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:56:25.630679Z

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 f0594368-e939-4ca7-af3f-aa44f51dab5e · outbound

This paper cites Enhancing Se- curity in Large Language Models: A Comprehensive Review of Prompt Injection Attacks and Defenses,.

Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs Enhancing Se- curity in Large Language Models: A Comprehensive Review of Prompt Injection Attacks and Defenses,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:56:25.608889Z

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 68ed8c8a-2986-4fa6-8660-8a55eea21f2d · outbound

This paper cites A Survey on Large Language Model Security and Privacy,.

Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs A Survey on Large Language Model Security and Privacy,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:56:25.594034Z

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 0852b5ac-dbb0-4938-8dd4-a5848b0a8729 · outbound

This paper cites LLM01:2025 Prompt Injection,.

Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs LLM01:2025 Prompt Injection,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:56:25.575229Z

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 b95f095c-b5d2-4953-8222-50f6ab109f9a · outbound

This paper cites A Single Poisoned Document Could Leak ‘Secret’ Data via ChatGPT,.

Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs A Single Poisoned Document Could Leak ‘Secret’ Data via ChatGPT,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:56:25.563032Z

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 77ce5282-0626-4bb9-a3ca-a4562fe2abb0 · outbound

This paper cites Hackers Hijacked Google’s Gemini AI With a Poisoned Calendar Invite,.

Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs Hackers Hijacked Google’s Gemini AI With a Poisoned Calendar Invite,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:56:25.550066Z

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 bcbd4941-d0ea-4a20-a979-323773f2445c · outbound

This paper cites This Prompt Can Make an AI Chat- bot Identify and Extract Personal Details,.

Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs This Prompt Can Make an AI Chat- bot Identify and Extract Personal Details,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:56:25.534529Z

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 5aa00c8a-89ef-4a36-b70f-ba1c40eab002 · outbound

This paper cites Here Come the AI Worms,.

Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs Here Come the AI Worms,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:56:25.516900Z

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 c1763a5b-856e-409b-8c1b-99dea9b2e0f0 · outbound

This paper cites Cybersecurity execs face a new battle- front: AI vs AI,.

Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs Cybersecurity execs face a new battle- front: AI vs AI,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:56:25.507072Z

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 e2c661f0-f44b-4c6a-b8f5-d75d15bfa09f · outbound

This paper cites Hackers ‘jailbreak’ powerful AI mod- els in global effort,.

Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs Hackers ‘jailbreak’ powerful AI mod- els in global effort,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:56:25.489336Z

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 5c84f511-aad6-438f-8964-9d05c9e93977 · outbound

This paper cites Multi-Stage Prompt Inference Attacks on Enterprise LLM Systems.

Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs Multi-Stage Prompt Inference Attacks on Enterprise LLM Systems

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T04:56:25.081296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 69860096-2df0-4791-9e24-7714f4f176ee · inbound

On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models cites this paper.

On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs

Reference 150

Resolution: verified exact; local_arxiv, observed 2026-08-15T14:21:43.164358Z

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.