Paper Citation Record · LEDGER

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt

As of 15 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 1 inbound Pith citation observation for arXiv:2506.05739.

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

pith.paper-citation-record.v1
2506.05739 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T10:19:29.189081Z

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-29T06:34:52.596684Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-29T14:33:31.438836Z

Reference resolution

38 of 38 outbound references displayed

verified exact0
verified fuzzy23
unresolved15
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0649b10d-f881-454c-9e28-2c901c6b6628 · outbound

This paper cites How Does Naming Affect LLMs on Code Analysis Tasks?.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt How Does Naming Affect LLMs on Code Analysis Tasks?

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T10:19:25.445223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e00af381-01fe-497c-a447-cbe3e9586384 · outbound

This paper cites Repair Is Nearly Generation: Multi- lingual Program Repair with LLMs,.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt Repair Is Nearly Generation: Multi- lingual Program Repair with LLMs,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:19:33.165141Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1a18f318-faa0-418a-b15f-77f92f3464ad · outbound

This paper cites Evaluating large language models for real-world vul- nerability repair in c/c++ code,.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt Evaluating large language models for real-world vul- nerability repair in c/c++ code,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:19:33.003046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 131add71-39e1-404f-99da-ec36a718da2e · outbound

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

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt Ignore Previous Prompt: Attack Techniques For Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T10:19:25.879894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cf7a326-7fb5-4c32-9a4e-b4b441dc7f5a · outbound

This paper cites Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T10:19:26.049365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7baee7c6-bd20-4af9-9ff4-c19d12886313 · outbound

This paper cites Safe RLHF: Safe Reinforcement Learning from Human Feedback.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt Safe RLHF: Safe Reinforcement Learning from Human Feedback

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T10:19:26.179955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45b0e32c-199c-4331-bb9c-b0ebaf8c72fe · outbound

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

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt Training language models to follow instructions with human feedback,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:19:32.804618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 47741064-91e7-4d67-ab2a-e61c9f05b7f6 · outbound

This paper cites Security and Privacy Challenges of Large Language Models: A Survey.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt Security and Privacy Challenges of Large Language Models: A Survey

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T10:19:26.510759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 274ad45c-598b-49a1-80be-6d60cbf83b65 · outbound

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

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt Prompt Injection attack against LLM-integrated Applications

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T10:19:26.602943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e037b44-6e8d-436d-84f2-70ab36640d69 · outbound

This paper cites JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T10:19:26.737973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26009b1c-491e-4704-98fe-6318e07a0af2 · outbound

This paper cites Adversarial Prompting in LLMs,.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt Adversarial Prompting in LLMs,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:19:32.627984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation bfae5d97-6b45-440f-a63b-d4395614c408 · outbound

This paper cites Jailbreak Attacks and Defenses Against Large Language Models: A Survey.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt Jailbreak Attacks and Defenses Against Large Language Models: A Survey

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T10:19:26.977002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdba7935-8599-4b6a-b737-0ce10d3b098e · outbound

This paper cites Prompt Injection: A Comprehensive Guide,.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt Prompt Injection: A Comprehensive Guide,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:19:32.473632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation abe78824-f39b-45df-9ce0-ec3ffd45b8a9 · outbound

This paper cites Self-Evaluation as a Defense Against Adversarial Attacks on LLMs.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt Self-Evaluation as a Defense Against Adversarial Attacks on LLMs

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T10:19:27.248071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45b0194a-561d-43d9-8c08-6267c1a28bc2 · outbound

This paper cites Formalizing and benchmarking prompt injection attacks and defenses,.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt Formalizing and benchmarking prompt injection attacks and defenses,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T10:19:27.389402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96ab407a-8a48-4913-b7da-bcf187ffe516 · outbound

This paper cites Prompt injection attacks against gpt- 3,.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt Prompt injection attacks against gpt- 3,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:19:32.298393Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b8587df2-1373-4b61-ae40-16046a07e868 · outbound

This paper cites An Early Categorization of Prompt Injection Attacks on Large Language Models.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt An Early Categorization of Prompt Injection Attacks on Large Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T10:19:27.647166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0a259b1-25a2-45b8-9082-ea88c08fdef6 · outbound

This paper cites Better Zero-Shot Reasoning with Role-Play Prompting.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt Better Zero-Shot Reasoning with Role-Play Prompting

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T10:19:27.745795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e58c5703-b5c2-48b3-9d39-2d17cd797252 · outbound

This paper cites Lakera pint benchmark,.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt Lakera pint benchmark,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:19:32.120677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 500c2f87-c31b-4e10-9d1c-90c022980452 · outbound

This paper cites Lakera guard,.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt Lakera guard,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:19:31.932251Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a0b7df2b-7ab4-4cb2-82e0-12e05a47fa72 · outbound

This paper cites Amazon bedrock guardrails,.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt Amazon bedrock guardrails,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:19:31.774757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 32122546-539e-4fd2-bf09-6d0a96c12ef7 · outbound

This paper cites deberta-v3-base-prompt-injection-v2,.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt deberta-v3-base-prompt-injection-v2,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:19:31.609448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 558f4c3e-8610-458e-813a-a0b1ce25db54 · outbound

This paper cites Prompt-guard-86m,.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt Prompt-guard-86m,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:19:31.400317Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation bf94cae6-80c4-4d2b-b631-fbef783bcb0c · outbound

This paper cites deberta-v3-base-prompt-injection,.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt deberta-v3-base-prompt-injection,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:19:31.206818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 33d26895-6d97-408e-b2a4-db4629d80590 · outbound

This paper cites Jailbreak detection in azure ai content safety,.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt Jailbreak detection in azure ai content safety,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:19:31.063676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 45c6ec60-6a61-4521-971c-5940c0e0831e · outbound

This paper cites Langkit,.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt Langkit,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:19:30.900752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ac9fb702-1e5d-4f88-865f-1eb06f38ddf9 · outbound

This paper cites Hyperion,.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt Hyperion,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:19:30.716482Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation eb8735e1-7ae1-4dfa-98ab-e2737ffc901b · outbound

This paper cites distilbert-prompt-injection,.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt distilbert-prompt-injection,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:19:30.453066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7c7281b8-4d39-4244-9f8d-1b1cb2ffca47 · outbound

This paper cites deepset/deberta-v3-base-injection,.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt deepset/deberta-v3-base-injection,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:19:30.287872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0afe1ba4-9550-4ca1-95fe-40353059ef9d · outbound

This paper cites setfit-prompt-injection-minilm-l3-v2,.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt setfit-prompt-injection-minilm-l3-v2,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:19:30.103815Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1603b887-b505-4a34-8d6e-dbdfaf762a35 · outbound

This paper cites GenTel-Safe: A Unified Benchmark and Shielding Framework for Defending Against Prompt Injection Attacks.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt GenTel-Safe: A Unified Benchmark and Shielding Framework for Defending Against Prompt Injection Attacks

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T10:19:28.764757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5debd830-fed0-465a-82e6-9663f7ce0a6f · outbound

This paper cites Hyperion,.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt Hyperion,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:19:29.979847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0790fb08-a6b7-4c05-9399-4a2322168d67 · outbound

This paper cites Whylabs langkit,.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt Whylabs langkit,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:19:29.897487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 108b383e-74e9-4d8f-96c8-25e9dfffed09 · outbound

This paper cites Baseline defenses for adversarial attacks against aligned language models,.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt Baseline defenses for adversarial attacks against aligned language models,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:19:29.801080Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3c8fb94b-4777-46e7-94ff-26744ae080af · outbound

This paper cites SPIN: Self-Supervised Prompt INjection.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt SPIN: Self-Supervised Prompt INjection

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T10:19:29.037606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f2592d3-4b80-4756-bf2a-7f45da7bafdc · outbound

This paper cites Defense Against Prompt Injection Attack by Leveraging Attack Techniques.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt Defense Against Prompt Injection Attack by Leveraging Attack Techniques

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T10:19:29.117892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e62fd7b-6eb0-491e-bc52-fff747fe3892 · outbound

This paper cites Promptshield: Deployable detection for prompt in- jection attacks,.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt Promptshield: Deployable detection for prompt in- jection attacks,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:19:29.616807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation aca54fdb-28d2-4006-a64f-b22406a03e97 · outbound

This paper cites Available: https://arxiv.org/abs/2309.

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt Available: https://arxiv.org/abs/2309

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:19:29.713100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Pith citing papers

Observation f9f5549e-2dd7-45dd-860a-6858e7ce6e1a · inbound

Strengthening Polymorphic Prompt Assembling: Dynamic Separator Generation Against Emerging Prompt Injection Attacks cites this paper.

Strengthening Polymorphic Prompt Assembling: Dynamic Separator Generation Against Emerging Prompt Injection Attacks To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-06-29T14:33:31.440394Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.