Paper Citation Record · LEDGER

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface

As of 11 August 2026, this Paper Citation Record lists 65 of 65 outbound references and 3 inbound Pith citation observations for arXiv:2501.09798.

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

pith.paper-citation-record.v1
2501.09798 v2

Coverage vector

measured 65 of 65 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T19:44:46.904083Z

measured 68 of 68 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 2026-08-07T14:27:03.532090Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-11T13:11:05.821591Z

Reference resolution

65 of 65 outbound references displayed

verified exact0
verified fuzzy29
unresolved36
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f531fd8f-6dbc-4390-b07b-5a4622807b87 · outbound

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

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.639882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60d09271-fd20-4f5d-b816-75ddb9df7c7b · outbound

This paper cites Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.645200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eeec835c-6ae5-4b0c-a97f-7b7d69dfebcc · outbound

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

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Baseline defenses for adversarial attacks against aligned language models,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.653268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 041d97c1-425e-47e7-b234-81c55f437710 · outbound

This paper cites Jailbroken: How does llm safety training fail?.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Jailbroken: How does llm safety training fail?

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:47.727265Z

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 69555f02-a8a2-4014-b92a-30e4fb5a17d8 · outbound

This paper cites GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.661476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbd0cc9b-3d60-4f52-8199-55df590bd38f · outbound

This paper cites Jailbreaking Attack against Multimodal Large Language Model.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Jailbreaking Attack against Multimodal Large Language Model

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.665840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0582cb30-de7d-42d4-9823-b62a3b495006 · outbound

This paper cites ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.670433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 284bb75e-10f3-4186-a285-4502491a817c · outbound

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

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injection,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:47.715548Z

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 9e50f171-f624-4d50-8d07-0ab676d86fb3 · outbound

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

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Prompt Injection attack against LLM-integrated Applications

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.677085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 874fa737-6b6a-454a-8515-af2d00b2b28d · outbound

This paper cites New prompt injection attack on chatgpt web version. markdown images can steal your chat data.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface New prompt injection attack on chatgpt web version. markdown images can steal your chat data

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:47.703708Z

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 6abfb145-4285-497e-a175-a8f024a47fbb · outbound

This paper cites InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.684263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0947bfe-05a8-4e3b-b10c-9625c6923823 · outbound

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

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.688359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd0138ba-04aa-4a41-bdc3-f2c85c7b16ae · outbound

This paper cites Agent hijacking: The true impact of prompt injection at- tacks,.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Agent hijacking: The true impact of prompt injection at- tacks,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:47.692359Z

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 df4d6799-3b1e-45af-bb27-35ae57aa8038 · outbound

This paper cites Fine-tuning with the Gemini API — Google AI for Devel- opers — ai.google.dev,.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Fine-tuning with the Gemini API — Google AI for Devel- opers — ai.google.dev,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:47.679867Z

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 cbd19d35-23e1-4f5b-b030-7eb255f68c41 · outbound

This paper cites Fine-tuning now available for gpt-4o,.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Fine-tuning now available for gpt-4o,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:47.667734Z

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 e5e97e32-ccee-4796-8b1d-8433776b4eaf · outbound

This paper cites Fine-tune anthropic’s claude 3 haiku in amazon bedrock to boost model accuracy and quality,.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Fine-tune anthropic’s claude 3 haiku in amazon bedrock to boost model accuracy and quality,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:47.655732Z

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 39b5467a-753a-4989-8449-08335e7142a4 · outbound

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

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.707471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df1b7af3-2a90-49b5-88c2-a10f74a78156 · outbound

This paper cites ChatGPT-Dan-Jailbreak,.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface ChatGPT-Dan-Jailbreak,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:47.643361Z

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 830119b9-2f3f-4a2c-8579-0330fb7470d1 · outbound

This paper cites Jailbreaking Black Box Large Language Models in Twenty Queries.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.715399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c865d34-941f-4f78-b930-4589adf615af · outbound

This paper cites Tree of attacks: Jailbreaking black-box llms automatically,.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Tree of attacks: Jailbreaking black-box llms automatically,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:47.632052Z

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 ad1b6a1a-8ff3-4c77-a6c1-ae048083257e · outbound

This paper cites Universal and transferable adversarial attacks on aligned language models,.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Universal and transferable adversarial attacks on aligned language models,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.723352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 979f79fe-c948-4161-a02f-42175b8737b5 · outbound

This paper cites Query-Based Adversarial Prompt Generation.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Query-Based Adversarial Prompt Generation

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.731684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ad8aee2-5358-44f7-adba-df9787fb43f8 · outbound

This paper cites AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.739609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b1ea4e5-f017-4a50-9cc3-5173d80d7fcb · outbound

This paper cites Chat create top logprobs — openai api refer- ence,.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Chat create top logprobs — openai api refer- ence,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:47.613923Z

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 e370eae3-f5b4-45f9-b058-acfa317bf3dc · outbound

This paper cites Generating content — Gemini API,.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Generating content — Gemini API,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:47.602801Z

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 5e7e3a1c-59f7-475f-a08d-89bca95f164c · outbound

This paper cites Stealing Part of a Production Language Model.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Stealing Part of a Production Language Model

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.751961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 889afef5-80b1-443f-a3a6-acb3d07690f1 · outbound

This paper cites Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.756162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76ea2f15-2dda-4a04-90a1-5214d73678b1 · outbound

This paper cites CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.760303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70f2dad5-0b57-4929-a353-aebc6abe5965 · outbound

This paper cites PAL: Proxy-Guided Black-Box Attack on Large Language Models.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface PAL: Proxy-Guided Black-Box Attack on Large Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.764390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d8c0595-1804-41eb-85a2-36422b8644b0 · outbound

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

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface StruQ: Defending Against Prompt Injection with Structured Queries

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.768410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e8fca0e-a0c3-4ad1-9b9a-e17578678e08 · outbound

This paper cites Finetuned language models are zero-shot learners,.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Finetuned language models are zero-shot learners,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:47.591077Z

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 d8e020f0-331e-440f-8dba-ddacd42d4c06 · outbound

This paper cites When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.775775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3ff758f-92c9-437a-9fc5-8ef4890a85fe · outbound

This paper cites The instruction hierarchy: Training llms to prioritize privileged instructions,.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface The instruction hierarchy: Training llms to prioritize privileged instructions,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:47.579417Z

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 a702172c-200f-4800-a189-51c164886adc · outbound

This paper cites Llm research insights: Instruction masking and new lora finetuning experiments,.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Llm research insights: Instruction masking and new lora finetuning experiments,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:47.568392Z

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 909ba9a7-ef16-40ae-b98b-793c3da831d8 · outbound

This paper cites Instruction Tuning With Loss Over Instructions.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Instruction Tuning With Loss Over Instructions

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.786002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54c4330b-5e63-4bcc-869e-9cd6dfe4d40a · outbound

This paper cites Sparse Fine-tuning for Inference Acceleration of Large Language Models.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Sparse Fine-tuning for Inference Acceleration of Large Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.790347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 956b3e1a-7c97-4f93-9ed8-1d7baf66e39f · outbound

This paper cites Neural exec: Learning (and learning from) execution triggers for prompt injection attacks,.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Neural exec: Learning (and learning from) execution triggers for prompt injection attacks,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:47.556926Z

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 60392b47-f5ed-4ec5-be81-7bfc74e844bc · outbound

This paper cites Gemma 2: Improving open language models at a practical size,.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Gemma 2: Improving open language models at a practical size,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:47.544728Z

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 62f003c0-4ac9-4449-ab33-00aea694a805 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.806608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c49828c7-1f66-41ec-a2e1-b3cf613228c5 · outbound

This paper cites How we estimate the risk from prompt injection attacks on ai sys- tems,.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface How we estimate the risk from prompt injection attacks on ai sys- tems,

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:47.532541Z

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 691bd998-7c7e-4e4e-91d5-eaeeab4f4852 · outbound

This paper cites Fine-tune claude 3 haiku,.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Fine-tune claude 3 haiku,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:47.518234Z

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 41e42d8c-0cb0-4a4f-9af1-fd9b8be56bbc · outbound

This paper cites Model tuning with gemini api,.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Model tuning with gemini api,

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:47.505794Z

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 42abb410-9fe1-4b6a-b6c3-850f0698ea8b · outbound

This paper cites Fine-tuning llms: Lora or full parameter? an in-depth analysis with llama 2,.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Fine-tuning llms: Lora or full parameter? an in-depth analysis with llama 2,

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:47.493310Z

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 04d99e7a-0746-4640-9a3e-8186ffb1655b · outbound

This paper cites Misusing Tools in Large Language Models With Visual Adversarial Examples.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Misusing Tools in Large Language Models With Visual Adversarial Examples

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.827770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ed86468-f91f-46a7-bcdf-c183ca47dce4 · outbound

This paper cites Ai injections: Direct and indirect prompt injections and their implications,.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Ai injections: Direct and indirect prompt injections and their implications,

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:47.481029Z

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 43a931c0-7846-4570-82dd-082507ba66fd · outbound

This paper cites Prompt injection: What’s the worst that can happen?.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Prompt injection: What’s the worst that can happen?

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:47.469176Z

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 b8f5ea0f-6eeb-4958-9fce-a19939c6fcae · outbound

This paper cites Ignore previous prompt: Attack techniques for language models,.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Ignore previous prompt: Attack techniques for language models,

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.839098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 132c74c1-6904-4ac5-9d06-277f13775b73 · outbound

This paper cites Multi-step Jailbreaking Privacy Attacks on ChatGPT.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Multi-step Jailbreaking Privacy Attacks on ChatGPT

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.843108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc805c16-701c-4902-91c1-58c597e2b13c · outbound

This paper cites Many-shot jailbreaking — anthropic.com,.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Many-shot jailbreaking — anthropic.com,

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:47.449893Z

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 7daffdd7-ab65-4638-b708-05b26b7d7940 · outbound

This paper cites OpenAI’s latest model will block the ‘ignore all previous instructions’ loophole,.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface OpenAI’s latest model will block the ‘ignore all previous instructions’ loophole,

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:47.437664Z

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 49f88a70-0a9e-490f-898d-375295fb61fd · outbound

This paper cites Fast Adversarial Attacks on Language Models In One GPU Minute.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Fast Adversarial Attacks on Language Models In One GPU Minute

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.854571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 037aa978-fbf3-465a-b1fb-fc1aadbb19f8 · outbound

This paper cites Poisoning language models during instruction tuning,.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Poisoning language models during instruction tuning,

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.858522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3d6893a-b1a3-42d2-8783-f956295b4005 · outbound

This paper cites Learning and Forgetting Unsafe Examples in Large Language Models.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Learning and Forgetting Unsafe Examples in Large Language Models

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.862115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e547205d-9d30-43e7-873b-91ecda930a92 · outbound

This paper cites Removing RLHF Protections in GPT-4 via Fine-Tuning.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Removing RLHF Protections in GPT-4 via Fine-Tuning

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.865919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be5c333d-8702-4505-9b94-04e4a47436e4 · outbound

This paper cites Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.869783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 930678c3-6d00-433f-958e-38e106789db1 · outbound

This paper cites Stealing machine learning models via prediction {APIs},.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Stealing machine learning models via prediction {APIs},

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:47.419382Z

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 9d987781-e7a1-462d-b8d5-b5710d4c8b5c · outbound

This paper cites Leaky dnn: Stealing deep-learning model secret with gpu context-switching side- channel,.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Leaky dnn: Stealing deep-learning model secret with gpu context-switching side- channel,

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:47.407941Z

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 7dcb638b-0c09-42fb-924f-565972851c8a · outbound

This paper cites On the sizes of openai api models,.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface On the sizes of openai api models,

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:47.395424Z

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 1d10e6f8-17ba-4e7d-9374-158774c915bf · outbound

This paper cites Anthropic tokenizer,.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Anthropic tokenizer,

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:47.383906Z

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 13e4e8dc-b042-4dcc-80ec-8668d70ebcc4 · outbound

This paper cites an unresolved cited work.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Unresolved cited work

Reference 63

Resolution: unresolved; raw_fallback, observed 2026-08-10T19:44:47.372357Z

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 db61c01e-0c12-4674-9cb6-43d7eede1420 · outbound

This paper cites an unresolved cited work.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Unresolved cited work

Reference 64

Resolution: unresolved; raw_fallback, observed 2026-08-10T19:44:47.361126Z

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 d9ae7401-df04-4bdc-95d9-9009817f3248 · outbound

This paper cites an unresolved cited work.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Unresolved cited work

Reference 65

Resolution: unresolved; raw_fallback, observed 2026-08-10T19:44:47.350698Z

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 1475143e-a480-42a2-9969-dfdf9bdea8bf · outbound

This paper cites Appendix C.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Appendix C

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:44:47.339635Z

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 fe648af9-ece8-4a51-8f46-d9d1f6dacd71 · outbound

This paper cites an unresolved cited work.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Unresolved cited work

Reference 67

Resolution: unresolved; raw_fallback, observed 2026-08-10T19:44:47.328186Z

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 27a7fa14-653a-47e3-aebd-1be0f2c28992 · outbound

This paper cites Neural Exec: Learning (and Learning from) Execution Triggers for Prompt Injection Attacks.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Neural Exec: Learning (and Learning from) Execution Triggers for Prompt Injection Attacks

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.798448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 30fba0b6-0662-48c2-9a97-08c7f135c1c9 · inbound

Security Concerns for Large Language Models: A Survey cites this paper.

Security Concerns for Large Language Models: A Survey Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:03.532090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b58182b9-d6e6-4d72-b42b-41026ce39bb6 · inbound

DART: Mitigating Harm Drift in Difference-Aware LLMs via Distill-Audit-Repair Training cites this paper.

DART: Mitigating Harm Drift in Difference-Aware LLMs via Distill-Audit-Repair Training Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T07:26:59.924242Z

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 08f49dd7-b7c0-4594-b5ef-a7477a85f05f · inbound

An AI Agent Execution Environment to Safeguard User Data cites this paper.

An AI Agent Execution Environment to Safeguard User Data Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:11:05.825940Z

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.