Paper Citation Record · LEDGER

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs

As of 8 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 0 inbound Pith citation observations for arXiv:2509.04615.

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

pith.paper-citation-record.v1
2509.04615 v1

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T05:59:28.771885Z

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+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

39 of 39 outbound references displayed

verified exact4
verified fuzzy10
unresolved25
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d699f37f-a263-477c-99ca-1399f0870c93 · outbound

This paper cites Jailbroken: How Does LLM Safety Training Fail?.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Jailbroken: How Does LLM Safety Training Fail?

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T05:59:27.764800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 136d3e88-d9a6-4115-8fb7-a6fef4e511d6 · outbound

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

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T05:59:27.810979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f0c4c94-9fea-4cec-b91e-ed6b9cb57b4e · outbound

This paper cites Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T05:59:27.941873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f297b84b-23f3-4024-89bd-8efb53814954 · outbound

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

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Prompt Injection attack against LLM-integrated Applications

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T05:59:28.044849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a206467c-f860-4403-8b1d-a41e70f2405d · outbound

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

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-05T05:59:28.139852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b63df69-81fe-40e7-a062-bae3a724ff7f · outbound

This paper cites PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T05:59:28.243698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 920fb974-f6f7-4760-8b40-0a8b9717d708 · outbound

This paper cites Black Box Adversarial Prompting for Foundation Models.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Black Box Adversarial Prompting for Foundation Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T05:59:28.348384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddf146e1-f23e-4c65-82b4-f542fbedbb27 · outbound

This paper cites A prompting-based approach for adversarial example generation and robustness enhancement,.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs A prompting-based approach for adversarial example generation and robustness enhancement,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T05:59:29.555851Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation bb8d0d41-f8b3-4413-999a-3e438355bff2 · outbound

This paper cites BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T05:59:28.656669Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2d41310-3d0c-4ca4-b2ec-0ba12563f06f · outbound

This paper cites Preemptive answer "attacks" on chain-of-thought reasoning,.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Preemptive answer "attacks" on chain-of-thought reasoning,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T05:59:29.543605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4166b559-ecfe-405c-863f-59b3cf19d032 · outbound

This paper cites Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T05:59:28.669109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31c492b0-4cdc-4a9f-8ee3-0cb730eaf08d · outbound

This paper cites Recent advancements in LLM Red-Teaming: Techniques, Defenses, and Ethical Considerations.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Recent advancements in LLM Red-Teaming: Techniques, Defenses, and Ethical Considerations

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T05:59:28.673407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac8b7e90-5ad0-47ad-9fc9-ef0b23088d0b · outbound

This paper cites Learning to Poison Large Language Models for Downstream Manipulation.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Learning to Poison Large Language Models for Downstream Manipulation

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T05:59:28.677245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce3add1f-4311-42ca-981e-7ac8553dd870 · outbound

This paper cites Scaling Trends for Data Poisoning in LLMs.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Scaling Trends for Data Poisoning in LLMs

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-05T05:59:28.681100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f18dd2eb-61be-4e89-ba1b-557fb7d014ed · outbound

This paper cites Jailbroken: How does llm safety training fail? In Advances in Neural Information Processing Systems ,.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Jailbroken: How does llm safety training fail? In Advances in Neural Information Processing Systems ,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T05:59:29.531127Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3b752784-8a50-4f11-b528-eb4749a35695 · outbound

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

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-05T05:59:28.692055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b419bb81-c754-4df2-939f-e073e4280b32 · outbound

This paper cites 0xk1h0 - github: Jailbreak prompts collection.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs 0xk1h0 - github: Jailbreak prompts collection

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T05:59:29.504988Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ea66c2d9-bbe0-46a2-b415-16fa02f1b69f · outbound

This paper cites Llm jailbreak | mitre atlas ™.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Llm jailbreak | mitre atlas ™

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T05:59:29.492141Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d2b95ec7-0475-4df8-b32d-ec2fb5e6ee97 · outbound

This paper cites Novel jailbreak technique via typoglycemia, 2023.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Novel jailbreak technique via typoglycemia, 2023

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-05T05:59:28.703514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12091326-8877-4c50-babf-be51316f30e1 · outbound

This paper cites Masterkey: Automated jailbreak across multiple large language model chatbots.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Masterkey: Automated jailbreak across multiple large language model chatbots

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T05:59:29.478533Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation bdc5b373-fe80-4ca4-8e9f-42aee80eec37 · outbound

This paper cites Exploiting programmatic behavior of llms: Dual-use through standard security attacks.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Exploiting programmatic behavior of llms: Dual-use through standard security attacks

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T05:59:28.715705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79d0d90e-e627-4d71-9c5f-4264af60fdc4 · outbound

This paper cites Prompt injection attacks in various llms, 2023.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Prompt injection attacks in various llms, 2023

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T05:59:29.465961Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6cf41b30-5d43-4d9c-8cf3-abccc6a0b67a · outbound

This paper cites Prompt injection attack on gpt-4, March 2023.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Prompt injection attack on gpt-4, March 2023

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T05:59:29.452580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 21332e49-ab08-4b7c-a50d-302f69aa472d · outbound

This paper cites MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-05T05:59:28.711730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fdcb0c3-9dff-4d51-9fb0-7ac8a5d4e349 · outbound

This paper cites Trojtext: Test-time invisible textual trojan insertion.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Trojtext: Test-time invisible textual trojan insertion

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T05:59:29.439908Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0463aaac-9cd0-4aae-a5bc-d727c3db5cf0 · outbound

This paper cites Trojan activation attack: Red-teaming large language models using activation steering for safety-alignment.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Trojan activation attack: Red-teaming large language models using activation steering for safety-alignment

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T05:59:28.737973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c70146f0-2fba-4554-9a18-c148d61dcb7e · outbound

This paper cites Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-05T05:59:28.741450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2d45d7c-98b6-4e49-a293-59861480529f · outbound

This paper cites Do llms have political correctness? analyzing ethical biases and jailbreak vulnerabilities in ai systems, 2024.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Do llms have political correctness? analyzing ethical biases and jailbreak vulnerabilities in ai systems, 2024

Reference 29

Resolution: verified exact; raw_fallback, observed 2026-08-05T05:59:28.947863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation daeb5318-2729-4486-a055-f242a92723be · outbound

This paper cites TrojText: Test-time Invisible Textual Trojan Insertion.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs TrojText: Test-time Invisible Textual Trojan Insertion

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-05T05:59:28.734338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cf2896e-0630-4c0a-9b3d-3b63fd7d33a7 · outbound

This paper cites Identifying and Mitigating Privacy Risks Stemming from Language Models: A Survey.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Identifying and Mitigating Privacy Risks Stemming from Language Models: A Survey

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-05T05:59:28.757303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56142a18-7a70-4c6b-8a25-c55c14c2c887 · outbound

This paper cites Reinforcement learning- driven LLM agent for automated attacks on LLMs.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Reinforcement learning- driven LLM agent for automated attacks on LLMs

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T05:59:29.426604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0848b3bf-217d-4a88-a68c-a14b3f7ecd1b · outbound

This paper cites LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-05T05:59:28.745638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69d64cda-7a28-4ee3-92a3-7ff35bf5818c · outbound

This paper cites Trojan Detection in Large Language Models: Insights from The Trojan Detection Challenge.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Trojan Detection in Large Language Models: Insights from The Trojan Detection Challenge

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-08-05T05:59:28.827636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 30070107-183b-4479-be43-53eb2f806334 · outbound

This paper cites Privacy Risks of General-Purpose AI Systems: A Foundation for Investigating Practitioner Perspectives.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Privacy Risks of General-Purpose AI Systems: A Foundation for Investigating Practitioner Perspectives

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-08-05T05:59:28.876110Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 47d134dd-4084-4a4e-96d4-d344fda06a2a · outbound

This paper cites TrojLLM: A Black-box Trojan Prompt Attack on Large Language Models.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs TrojLLM: A Black-box Trojan Prompt Attack on Large Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-05T05:59:28.764525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e12e604a-c60c-47cb-9b38-7618463c417f · outbound

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

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-05T05:59:28.771885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a3834ad-20da-4726-a80a-0dce4755644f · outbound

This paper cites A Prompting-based Approach for Adversarial Example Generation and Robustness Enhancement.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs A Prompting-based Approach for Adversarial Example Generation and Robustness Enhancement

Reference 2022

Resolution: verified exact; local_arxiv, observed 2026-08-05T05:59:29.314470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5b3fb305-7b4d-4a36-a6fd-9e796798e7d7 · outbound

This paper cites an unresolved cited work.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Unresolved cited work

Reference 2023

Resolution: unresolved; raw_fallback, observed 2026-08-05T05:59:29.517816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6e3a9bb8-c7aa-43d2-85e9-c7a7d309a71e · outbound

This paper cites Preemptive Answer "Attacks" on Chain-of-Thought Reasoning.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Preemptive Answer "Attacks" on Chain-of-Thought Reasoning

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-05T05:59:28.665142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.