Paper Citation Record · LEDGER

PromptShield: Deployable Detection for Prompt Injection Attacks

As of 11 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 3 inbound Pith citation observations for arXiv:2501.15145.

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

pith.paper-citation-record.v1
2501.15145 v2

Coverage vector

measured 43 of 43 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T14:38:10.831214Z

measured 46 of 46 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 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T15:42:00.944376Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T22:51:28.498764Z

Reference resolution

43 of 43 outbound references displayed

verified exact0
verified fuzzy2
unresolved41
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a9b0e2eb-903f-4636-8665-20e675895086 · outbound

This paper cites Synthetic Python Problems(SPP) Dataset.

PromptShield: Deployable Detection for Prompt Injection Attacks Synthetic Python Problems(SPP) Dataset

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:38:11.422630Z

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.

Observation 36789142-a7ab-4226-9758-8c02a1c5878e · outbound

This paper cites an unresolved cited work.

PromptShield: Deployable Detection for Prompt Injection Attacks Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-10T14:38:11.411292Z

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.

Observation b4123771-61eb-4ed3-a78a-1c1f87e2bb74 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

PromptShield: Deployable Detection for Prompt Injection Attacks Evaluating Large Language Models Trained on Code

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.663848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a101140-b35d-40a9-8e31-31de44155a63 · outbound

This paper cites an unresolved cited work.

PromptShield: Deployable Detection for Prompt Injection Attacks Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-10T14:38:11.400205Z

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.

Observation c1a4e108-e2e6-4b2e-9b53-f1cb3e6f091b · outbound

This paper cites an unresolved cited work.

PromptShield: Deployable Detection for Prompt Injection Attacks Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-10T14:38:11.389301Z

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.

Observation 0bea6be7-c00d-4a10-b2ce-9485abc9f5e0 · outbound

This paper cites Enhancing Chat Language Models by Scaling High-quality Instructional Conversations.

PromptShield: Deployable Detection for Prompt Injection Attacks Enhancing Chat Language Models by Scaling High-quality Instructional Conversations

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.684491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f758adff-8c80-43eb-b06f-7ef53093eb12 · outbound

This paper cites The Llama 3 Herd of Models.

PromptShield: Deployable Detection for Prompt Injection Attacks The Llama 3 Herd of Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.689007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbc2aa10-db96-429b-aaa1-a98bad8c4ef6 · outbound

This paper cites Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection.

PromptShield: Deployable Detection for Prompt Injection Attacks Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.694084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 430734d5-0bb4-45a0-a7b5-c64c1fbfdc8b · outbound

This paper cites DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing.

PromptShield: Deployable Detection for Prompt Injection Attacks DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.698026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e929d92-b2ea-4cdd-9efd-3a711c335683 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

PromptShield: Deployable Detection for Prompt Injection Attacks LoRA: Low-Rank Adaptation of Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.702531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa8ae770-decd-434f-9019-873469b9d942 · outbound

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

PromptShield: Deployable Detection for Prompt Injection Attacks Attention Tracker: Detecting Prompt Injection Attacks in LLMs

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.707493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdc94ba1-f4e0-4a7b-90e8-0d987d8a083d · outbound

This paper cites Challenges and Applications of Large Language Models.

PromptShield: Deployable Detection for Prompt Injection Attacks Challenges and Applications of Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.711675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb4b1d80-ee42-47ef-97bb-5c0b891f7f69 · outbound

This paper cites InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models.

PromptShield: Deployable Detection for Prompt Injection Attacks InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.715889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a570b69-e696-44b6-95e1-7fe185baa0b3 · outbound

This paper cites an unresolved cited work.

PromptShield: Deployable Detection for Prompt Injection Attacks Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.720746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ec546d2-09b4-454d-8931-417970feef7e · outbound

This paper cites an unresolved cited work.

PromptShield: Deployable Detection for Prompt Injection Attacks Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-10T14:38:11.358799Z

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.

Observation ae868522-a959-4baa-b726-6accbe7b7d78 · outbound

This paper cites an unresolved cited work.

PromptShield: Deployable Detection for Prompt Injection Attacks Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-10T14:38:11.347571Z

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.

Observation a449f3a9-6ad2-4080-8ef6-29338e173cee · outbound

This paper cites GPT-4 Technical Report.

PromptShield: Deployable Detection for Prompt Injection Attacks GPT-4 Technical Report

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.738851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cada18d-5cce-4dc4-933c-4c10486c5a70 · outbound

This paper cites Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al.

PromptShield: Deployable Detection for Prompt Injection Attacks Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.743167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed18f4c6-1517-4f7b-a14f-541740e2ccbe · outbound

This paper cites Ignore Previous Prompt: Attack Techniques For Language Models.

PromptShield: Deployable Detection for Prompt Injection Attacks Ignore Previous Prompt: Attack Techniques For Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.752114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd390d15-0022-45d2-88a3-f93878cbf92f · outbound

This paper cites Jatmo: Prompt Injection Defense by Task-Specific Finetuning.

PromptShield: Deployable Detection for Prompt Injection Attacks Jatmo: Prompt Injection Defense by Task-Specific Finetuning

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.756911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d306e8c6-4453-470b-87f5-bc4c825e1ff2 · outbound

This paper cites an unresolved cited work.

PromptShield: Deployable Detection for Prompt Injection Attacks Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-10T14:38:11.327290Z

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.

Observation a4944b51-6881-4a3f-98cc-bc88dbeaae2b · outbound

This paper cites an unresolved cited work.

PromptShield: Deployable Detection for Prompt Injection Attacks Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-10T14:38:11.314722Z

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.

Observation ea31d402-a21e-4380-a1cb-175ead1a2da6 · outbound

This paper cites Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks.

PromptShield: Deployable Detection for Prompt Injection Attacks Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.768234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a3c8de3-e72f-42e5-9b9b-750ed42eba3e · outbound

This paper cites Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition.

PromptShield: Deployable Detection for Prompt Injection Attacks Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.772475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d4a26dc-8e4d-407d-98e8-7b3ce237e84d · outbound

This paper cites "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models.

PromptShield: Deployable Detection for Prompt Injection Attacks "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.776605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e954736d-74ad-432f-bd8f-3297b2cc3764 · outbound

This paper cites an unresolved cited work.

PromptShield: Deployable Detection for Prompt Injection Attacks Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-10T14:38:11.303077Z

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.

Observation 6daeda31-1370-4c4c-b7da-e9c02c435b21 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

PromptShield: Deployable Detection for Prompt Injection Attacks Gemini: A Family of Highly Capable Multimodal Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.784378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9031ac05-1c26-46a1-b7ab-8a8391e3d086 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

PromptShield: Deployable Detection for Prompt Injection Attacks LLaMA: Open and Efficient Foundation Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.788382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49c8ba2b-bfea-4f87-aeb7-6f2aa4cd2269 · outbound

This paper cites The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions.

PromptShield: Deployable Detection for Prompt Injection Attacks The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.792153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d80e17d-1ac1-4b7c-befd-95140e1ca5c4 · outbound

This paper cites CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models.

PromptShield: Deployable Detection for Prompt Injection Attacks CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.796063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e641870-270d-4651-ae70-77cf1ce74a13 · outbound

This paper cites Self-Instruct: Aligning Language Models with Self-Generated Instructions.

PromptShield: Deployable Detection for Prompt Injection Attacks Self-Instruct: Aligning Language Models with Self-Generated Instructions

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.800055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccf65128-c3b4-44fe-8758-92a5eace32ac · outbound

This paper cites Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks.

PromptShield: Deployable Detection for Prompt Injection Attacks Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.804159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28f8851d-78e6-46dc-9232-b2b29d79ece2 · outbound

This paper cites Finetuned Language Models Are Zero-Shot Learners.

PromptShield: Deployable Detection for Prompt Injection Attacks Finetuned Language Models Are Zero-Shot Learners

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.808151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0175743d-88fe-4eb6-9851-69008c436cdf · outbound

This paper cites Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations.

PromptShield: Deployable Detection for Prompt Injection Attacks Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.811952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5624ae63-1e2e-44db-a517-e2a5e557d6a0 · outbound

This paper cites an unresolved cited work.

PromptShield: Deployable Detection for Prompt Injection Attacks Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-10T14:38:11.290763Z

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.

Observation cdda15a5-3796-4d18-9e1a-2d542bc05a47 · outbound

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

PromptShield: Deployable Detection for Prompt Injection Attacks Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.819685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation defdacfd-8992-4a0f-83f2-a13ab9707d1d · outbound

This paper cites LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset.

PromptShield: Deployable Detection for Prompt Injection Attacks LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.823352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 596a5622-8e09-4e7a-9b5e-185a8ea05ab8 · outbound

This paper cites Instruction-Following Evaluation for Large Language Models.

PromptShield: Deployable Detection for Prompt Injection Attacks Instruction-Following Evaluation for Large Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.827282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6738e3dd-4006-41f4-b406-2220d1abe217 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

PromptShield: Deployable Detection for Prompt Injection Attacks Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.831214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1460b56-bd4c-464d-b07b-71b262190cb2 · outbound

This paper cites Training language models to follow instructions with human feedback.

PromptShield: Deployable Detection for Prompt Injection Attacks Training language models to follow instructions with human feedback

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.747784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6211f10-57d6-4d7d-a37a-1691415c0ff9 · outbound

This paper cites https://www.databricks.com/blog/2023/04/12/dolly-first-open- commercially-viable-instruction-tuned-llm.

PromptShield: Deployable Detection for Prompt Injection Attacks https://www.databricks.com/blog/2023/04/12/dolly-first-open- commercially-viable-instruction-tuned-llm

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:38:11.377794Z

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.

Observation dd7110e7-c90d-42a0-9c3c-d11d2a2c5e90 · outbound

This paper cites In USENIX Security 2024.

PromptShield: Deployable Detection for Prompt Injection Attacks In USENIX Security 2024

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.727112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56b49855-31aa-49e4-bd2c-99e7ed05df51 · outbound

This paper cites StruQ: Defending Against Prompt Injection with Structured Queries.

PromptShield: Deployable Detection for Prompt Injection Attacks StruQ: Defending Against Prompt Injection with Structured Queries

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.672411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 6fb7aee4-2f44-4257-8920-b8e04a98c701 · inbound

PromptArmor: Simple yet Effective Prompt Injection Defenses cites this paper.

PromptArmor: Simple yet Effective Prompt Injection Defenses PromptShield: Deployable Detection for Prompt Injection Attacks

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T15:42:00.944376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dda0473a-f068-48a5-b58b-73328a2d860b · inbound

Quantifying Conversation Drift in MCP via Latent Polytope cites this paper.

Quantifying Conversation Drift in MCP via Latent Polytope PromptShield: Deployable Detection for Prompt Injection Attacks

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-08-05T22:51:28.507399Z

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.

Observation c5cea3cc-776f-49a5-ad13-96b85ee5c4f6 · inbound

Data Leakage Prevention in Agentic Applications via Preemptive Hardening cites this paper.

Data Leakage Prevention in Agentic Applications via Preemptive Hardening PromptShield: Deployable Detection for Prompt Injection Attacks

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T14:11:22.404653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.