Paper Citation Record · LEDGER

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior

As of 7 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 1 inbound Pith citation observation for arXiv:2508.19287.

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

pith.paper-citation-record.v1
2508.19287 v1

Coverage vector

measured 24 of 24 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T16:50:30.164447Z

measured 25 of 25 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-16T20:35:26.913297Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-16T20:38:24.771300Z

Reference resolution

24 of 24 outbound references displayed

verified exact0
verified fuzzy12
unresolved12
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 51f4e2e7-c5d4-42f7-afdd-3afe1c2a4c52 · outbound

This paper cites ACM transactions on intelligent systems and technology15(3), 1–45 (2024).

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior ACM transactions on intelligent systems and technology15(3), 1–45 (2024)

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T16:50:27.494758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de5726b3-e7be-433a-93fa-166858f3d9f7 · outbound

This paper cites A Survey on Large Language Models for Critical Societal Domains: Finance, Healthcare, and Law.

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior A Survey on Large Language Models for Critical Societal Domains: Finance, Healthcare, and Law

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T16:50:27.634779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a63a6e7-42f6-4b35-aa27-26ada5b07f9c · outbound

This paper cites In: 2024 IEEE International Con- ference on Big Data (BigData).

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior In: 2024 IEEE International Con- ference on Big Data (BigData)

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:50:33.494758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9425f9b0-6670-4106-ac45-82dab32a6e95 · outbound

This paper cites ACM Computing Surveys57(6), 1–39 (2025).

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior ACM Computing Surveys57(6), 1–39 (2025)

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:50:33.273793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 403147c1-9106-4219-b38b-f80faf053944 · outbound

This paper cites Cybersecurity 7(1), 70 (2024).

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior Cybersecurity 7(1), 70 (2024)

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:50:33.091436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation feb22126-f6bb-44ed-8bc7-a351c3db93b0 · outbound

This paper cites Defending Against Indirect Prompt Injection Attacks With Spotlighting.

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior Defending Against Indirect Prompt Injection Attacks With Spotlighting

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T16:50:28.069437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff8cef0a-4330-4753-93d2-389d03bf037a · outbound

This paper cites Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey.

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T16:50:28.169744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d5cf4f4-7742-48fa-bdb3-4c6ab5f5e6f6 · outbound

This paper cites Learning and individual differences103, 102274 (2023).

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior Learning and individual differences103, 102274 (2023)

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T16:50:28.278771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c70fa357-aa86-4b2e-ac33-2bb0ded3bc52 · outbound

This paper cites Authorea Preprints (2024).

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior Authorea Preprints (2024)

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:50:32.767031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e4a18588-d5ed-480c-846e-b7310ed07eb6 · outbound

This paper cites AI Open (2024).

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior AI Open (2024)

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:50:32.644754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a5848cdb-b43b-41a8-93ca-942c2cec5a0f · outbound

This paper cites In: Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems.

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior In: Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:50:32.410186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3d6c04de-94bf-46a0-8d38-b9f81cb1466a · outbound

This paper cites Advances in Neural Information Processing Systems36, 4952–4984 (2023).

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior Advances in Neural Information Processing Systems36, 4952–4984 (2023)

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:50:32.093373Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4b2a9e2e-c0a5-44ec-8b75-efc62a07db9b · outbound

This paper cites Automatic and Universal Prompt Injection Attacks against Large Language Models.

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior Automatic and Universal Prompt Injection Attacks against Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T16:50:28.896342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cde4d3ad-3e5c-4a5a-980c-90e767a3682e · outbound

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

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior In: 33rd USENIX Security Symposium (USENIX Security 24)

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:50:31.854751Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 82aeb5b6-db47-4b5d-bf7e-3e10af776f8b · outbound

This paper cites International Journal of Open Information Technologies12(5), 39– 48 (2024).

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior International Journal of Open Information Technologies12(5), 39– 48 (2024)

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:50:31.524753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f8b6f0db-3eef-4e6d-8105-3ddec786ad55 · outbound

This paper cites Cluster Computing 27(1), 1–26 (2024).

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior Cluster Computing 27(1), 1–26 (2024)

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:50:31.195817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 96a786cc-3e7a-40cb-bea5-4d75596676d6 · outbound

This paper cites Available at SSRN 5017385.

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior Available at SSRN 5017385

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:50:30.922498Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f37e7852-2c04-42ea-a321-2f6e4f3ebbb5 · outbound

This paper cites In: 2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior In: 2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:50:30.774749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 93c46095-eab8-44ac-a4ca-608cc6f2cda2 · outbound

This paper cites Safeguarding Crowdsourcing Surveys from ChatGPT with Prompt Injection.

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior Safeguarding Crowdsourcing Surveys from ChatGPT with Prompt Injection

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-05T16:50:29.576676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72435f72-57a9-4523-bade-16d154b3f501 · outbound

This paper cites FATH: Authentication-based Test-time Defense against Indirect Prompt Injection Attacks.

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior FATH: Authentication-based Test-time Defense against Indirect Prompt Injection Attacks

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T16:50:29.700036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ed72736-4654-47a2-8294-25c22ec8fd0e · outbound

This paper cites A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems.

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T16:50:29.805387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3cba737-1295-4552-94ac-1eadc91f1413 · outbound

This paper cites Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models.

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-05T16:50:29.954752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc15fc42-8896-4481-8e38-5ef69530383c · outbound

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

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior Goal-guided Generative Prompt Injection Attack on Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T16:50:30.014754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e909c49-7e05-45ab-9c3e-2c0063b2b161 · outbound

This paper cites an unresolved cited work.

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-05T16:50:30.574959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Pith citing papers

Observation 8b997909-ea2a-4798-a6bb-7b9687af6c4d · inbound

ChatGPT: Excellent Paper! Accept It. Editor: Imposter Found! Review Rejected cites this paper.

ChatGPT: Excellent Paper! Accept It. Editor: Imposter Found! Review Rejected Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-16T20:38:24.772785Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.