Paper Citation Record · LEDGER

Breaking the Prompt Wall (I): A Real-World Case Study of Attacking ChatGPT via Lightweight Prompt Injection

As of 18 August 2026, this Paper Citation Record lists 11 of 11 outbound references and 2 inbound Pith citation observations for arXiv:2504.16125.

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

pith.paper-citation-record.v1
2504.16125 v1

Coverage vector

measured 11 of 11 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T11:51:19.347084Z

measured 13 of 13 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T22:42:00.220522Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-29T07:53:14.251868Z

Reference resolution

11 of 11 outbound references displayed

verified exact0
verified fuzzy2
unresolved9
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 42914bb6-783b-4be7-bff1-cd4e6e2ba38e · outbound

This paper cites Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks.

Breaking the Prompt Wall (I): A Real-World Case Study of Attacking ChatGPT via Lightweight Prompt Injection Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T11:51:19.294095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d91d227-ed24-4d42-a1ed-fec5097fcf60 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Breaking the Prompt Wall (I): A Real-World Case Study of Attacking ChatGPT via Lightweight Prompt Injection DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T11:51:19.300489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d86aba4-ad65-4b83-8b26-c6910b1224b6 · outbound

This paper cites Proadvprompter: A two-stage journey to effective adversarial prompting for llms.

Breaking the Prompt Wall (I): A Real-World Case Study of Attacking ChatGPT via Lightweight Prompt Injection Proadvprompter: A two-stage journey to effective adversarial prompting for llms

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:51:19.684368Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a27606d8-1141-469e-bafe-a4b2e1e093bb · outbound

This paper cites Not what you've signed up for: Compromising real-world llm-integrated applications with indirect prompt injection.

Breaking the Prompt Wall (I): A Real-World Case Study of Attacking ChatGPT via Lightweight Prompt Injection Not what you've signed up for: Compromising real-world llm-integrated applications with indirect prompt injection

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T11:51:19.310480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cdc0751-ebd9-42b3-831c-9a1c4771744f · outbound

This paper cites Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety.

Breaking the Prompt Wall (I): A Real-World Case Study of Attacking ChatGPT via Lightweight Prompt Injection Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T11:51:19.315822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b74f87d-3394-4c08-9711-99747329ae11 · outbound

This paper cites Gpt-4 technical report.

Breaking the Prompt Wall (I): A Real-World Case Study of Attacking ChatGPT via Lightweight Prompt Injection Gpt-4 technical report

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:51:19.667174Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 155949d7-f206-41f0-ad84-bccad8100678 · outbound

This paper cites Can LLM feedback enhance review quality? A randomized study of 20K reviews at ICLR 2025.

Breaking the Prompt Wall (I): A Real-World Case Study of Attacking ChatGPT via Lightweight Prompt Injection Can LLM feedback enhance review quality? A randomized study of 20K reviews at ICLR 2025

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T11:51:19.326275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1090ee2b-dafc-4d09-b139-2ec4d5d11e4a · outbound

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

Breaking the Prompt Wall (I): A Real-World Case Study of Attacking ChatGPT via Lightweight Prompt Injection LLaMA: Open and Efficient Foundation Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T11:51:19.331250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f125c16-4690-4113-bb8d-174f11e7d900 · outbound

This paper cites BloombergGPT: A Large Language Model for Finance.

Breaking the Prompt Wall (I): A Real-World Case Study of Attacking ChatGPT via Lightweight Prompt Injection BloombergGPT: A Large Language Model for Finance

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T11:51:19.336394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd659707-9fc2-4a6c-a885-baf3b9b2cc54 · outbound

This paper cites Fingpt: Open-source financial large language models.

Breaking the Prompt Wall (I): A Real-World Case Study of Attacking ChatGPT via Lightweight Prompt Injection Fingpt: Open-source financial large language models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T11:51:19.341554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9b89c34-37b7-4eea-8444-dd10820ef57a · outbound

This paper cites Are We There Yet? Revealing the Risks of Utilizing Large Language Models in Scholarly Peer Review.

Breaking the Prompt Wall (I): A Real-World Case Study of Attacking ChatGPT via Lightweight Prompt Injection Are We There Yet? Revealing the Risks of Utilizing Large Language Models in Scholarly Peer Review

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T11:51:19.347084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 16a5338f-783f-4b6c-affa-7540ac4846f9 · inbound

Practical Reasoning Interruption Attacks on Reasoning Large Language Models cites this paper.

Practical Reasoning Interruption Attacks on Reasoning Large Language Models Breaking the Prompt Wall (I): A Real-World Case Study of Attacking ChatGPT via Lightweight Prompt Injection

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T22:42:00.220522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2bc39bf-1d4f-4427-8be6-76205425af09 · inbound

Provably Secure Agent Guardrail cites this paper.

Provably Secure Agent Guardrail Breaking the Prompt Wall (I): A Real-World Case Study of Attacking ChatGPT via Lightweight Prompt Injection

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-06-29T07:53:14.253813Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.