Paper Citation Record · LEDGER

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs

As of 12 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 0 inbound Pith citation observations for arXiv:2607.19396.

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

pith.paper-citation-record.v1
2607.19396 v2

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T04:34:33.230801Z

measured 35 of 35 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 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

35 of 35 outbound references displayed

verified exact0
verified fuzzy0
unresolved35
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7e9fc0e5-ceab-4697-a853-8c3e430e8b59 · outbound

This paper cites LLM01 2025 Prompt Injection.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs LLM01 2025 Prompt Injection

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.136025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2d46ee9-a217-4822-b758-2ae655dfca69 · outbound

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

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs Prompt Injection attack against LLM-integrated Applications

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.139765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4a59186-71d9-44ec-b488-2dc8b5ea83ae · outbound

This paper cites https://arxiv.org/abs/2601.22240.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs https://arxiv.org/abs/2601.22240

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.143131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c78452c-6067-4834-8201-8f759a989443 · outbound

This paper cites Prompt Injection Defenses.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs Prompt Injection Defenses

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.146158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e2e8e2d-4f66-43d6-9414-b42be40666af · outbound

This paper cites Principled Detection of Hidden LLM Prompts in Structured Documents.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs Principled Detection of Hidden LLM Prompts in Structured Documents

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.149047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 622b2666-1d48-4187-b117-e8869480b7b4 · outbound

This paper cites Hidden-Comment Injection in LLM Agents.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs Hidden-Comment Injection in LLM Agents

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.152202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d01d33a-8052-4cbb-b240-7438ab46b225 · outbound

This paper cites Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Models.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.155021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f35fa40f-b88d-49c5-bed0-ef32a46321db · outbound

This paper cites https://arxiv.org/pdf/2509.10248.pdf.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs https://arxiv.org/pdf/2509.10248.pdf

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.158239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f78d466c-b906-4e2f-9e31-08ec29d6eae6 · outbound

This paper cites https://arxiv.org/abs/2512.23684.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs https://arxiv.org/abs/2512.23684

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.161193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 691ddd70-931d-4022-8422-016be9d95880 · outbound

This paper cites https://zenodo.org/records/16603590.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs https://zenodo.org/records/16603590

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.163875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b995a757-5a36-469b-bc45-c331308d780c · outbound

This paper cites Prompt Injection Exploits Invisible PDF Text to Pass Credit Score Analysis.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs Prompt Injection Exploits Invisible PDF Text to Pass Credit Score Analysis

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.166564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07d92953-b41f-42ef-8665-0ac89e799c8d · outbound

This paper cites Invisible Prompt Injection Secure AI.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs Invisible Prompt Injection Secure AI

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.169371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae316f90-7e56-439c-80eb-9dc0b1cd4ea3 · outbound

This paper cites Invisible Unicode Jailbreak.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs Invisible Unicode Jailbreak

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.172135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd443f65-e50b-4d29-a4f1-52610b00f23f · outbound

This paper cites Attention Tracker: Detecting Prompt Injection Attacks in LLMs.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs Attention Tracker: Detecting Prompt Injection Attacks in LLMs

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.174989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fb72c58-e0cf-46e2-aa67-771be435e741 · outbound

This paper cites Prompt Guard: Model Card formeta-llama/Prompt-Guard-86M.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs Prompt Guard: Model Card formeta-llama/Prompt-Guard-86M

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.178043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0dfbe7e4-bdf8-4b15-8bcb-fc390c094bb3 · outbound

This paper cites Llama-Prompt-Guard-2-86M.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs Llama-Prompt-Guard-2-86M

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.180706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4d5d6f6-8c08-4815-9c41-571f3634349c · outbound

This paper cites Detection Method for Prompt Injection by Integrating Pre-trained Model and Heuristic Feature Engineering.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs Detection Method for Prompt Injection by Integrating Pre-trained Model and Heuristic Feature Engineering

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.183294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90936c11-4b0a-4254-89a1-a7524fea8d45 · outbound

This paper cites https://arxiv.org/abs/2512.12583.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs https://arxiv.org/abs/2512.12583

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.186139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab1cab5e-ed91-4d50-abdf-547d49ec9374 · outbound

This paper cites https://media.sciltp.com/articles/2506000841/2506000841.pdf.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs https://media.sciltp.com/articles/2506000841/2506000841.pdf

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.188808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5b5b6f3-5ca6-4c70-8852-9a1e12bbb827 · outbound

This paper cites Zero-Shot Embedding Drift Detection: A Lightweight Defense Against Prompt Injections in LLMs.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs Zero-Shot Embedding Drift Detection: A Lightweight Defense Against Prompt Injections in LLMs

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.191346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6df1d6e5-8472-4e1c-b501-1690c69b0000 · outbound

This paper cites CAPTURE: Context-Aware Prompt Injection Testing and Robustness Enhancement.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs CAPTURE: Context-Aware Prompt Injection Testing and Robustness Enhancement

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.194213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17312f1f-3afc-4609-a316-eba417007acf · outbound

This paper cites Content Masking Attack Against Information-Based Online Services.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs Content Masking Attack Against Information-Based Online Services

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.197394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61f841c8-3312-4635-86dd-ab0f85ef38bb · outbound

This paper cites Studying, Finding, and Localizing Inconsistency Bugs in PDF Readers and Files.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs Studying, Finding, and Localizing Inconsistency Bugs in PDF Readers and Files

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.200076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a81d8904-f1e6-4e33-9b56-5145fcb26790 · outbound

This paper cites https://www.usenix.org/system/files/sec20-chen-yizheng.pdf.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs https://www.usenix.org/system/files/sec20-chen-yizheng.pdf

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.202834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8086476-c70b-43b3-8feb-79337ef64ad2 · outbound

This paper cites https://www.emergentmind.com/topics/optical-character-recognition-ocr-exploits.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs https://www.emergentmind.com/topics/optical-character-recognition-ocr-exploits

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.205481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d76c050-0437-4331-ac7b-13b0f5c57a91 · outbound

This paper cites PDF Document Security.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs PDF Document Security

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.208166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

This paper cites Manipulating Multimodal Agents via Cross-Modal Prompt Injection.

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.

Observation 056b3cb0-8cb2-462c-b6f4-b897d640491e · outbound

This paper cites https://pmc.ncbi.nlm.nih.gov/articles/PMC4993050/.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs https://pmc.ncbi.nlm.nih.gov/articles/PMC4993050/

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.213268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fb4000e-e920-43da-9f19-5a92d83720b5 · outbound

This paper cites https://www.cs.cornell.edu/fbs/publications/Hyperproperties.pdf.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs https://www.cs.cornell.edu/fbs/publications/Hyperproperties.pdf

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.215886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa77f827-694c-4126-afe4-e688d5d5da55 · outbound

This paper cites https://proglearn.neurodata.io/experiments/label_shuffle_exp.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs https://proglearn.neurodata.io/experiments/label_shuffle_exp

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.218576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e52b2135-8bdc-4e8f-af6f-904e6450af54 · outbound

This paper cites Sanity Checks for Explanation Uncertainty.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs Sanity Checks for Explanation Uncertainty

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.221037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d17f9d6-8de5-4a8a-9428-9fb90c9532ac · outbound

This paper cites Machine Learning Crash Course ROC and AUC.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs Machine Learning Crash Course ROC and AUC

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.223606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa54ae66-5b20-42fa-b3f2-5d0f37c845fa · outbound

This paper cites PDFAutoGen: Automated Benchmark Construction Pipeline for Hidden Prompt Injection Detection in PDFs.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs PDFAutoGen: Automated Benchmark Construction Pipeline for Hidden Prompt Injection Detection in PDFs

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.226021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3758af88-8483-471a-91e8-1fca1cca36db · outbound

This paper cites LLM Jailbreak & Prompt-Injection Dataset.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs LLM Jailbreak & Prompt-Injection Dataset

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.228420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab5d4a4c-a314-4f05-a53f-30c812d08329 · outbound

This paper cites Prompt Injection and Jailbreak Detection Dataset.

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs Prompt Injection and Jailbreak Detection Dataset

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T04:34:33.230801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.