Paper Citation Record · LEDGER

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses

As of 15 August 2026, this Paper Citation Record lists 100 of 255 outbound references and 3 inbound Pith citation observations for arXiv:2510.15476.

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

pith.paper-citation-record.v1
2510.15476 v3

Coverage vector

measured 100 of 255 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T09:25:45.961893Z

measured 103 of 103 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 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T00:32:02.668360Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T20:00:07.826531Z

Reference resolution

100 of 255 outbound references displayed

verified exact0
verified fuzzy0
unresolved99
parse uncertain1
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9b9a8f4d-0a44-4fef-974e-f8169200dfc4 · outbound

This paper cites glaive-code-assistant, 2023.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses glaive-code-assistant, 2023

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:35.805221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation baf3582e-15f8-4574-8754-8951849bde68 · outbound

This paper cites Detecting Language Model Attacks with Perplexity.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Detecting Language Model Attacks with Perplexity

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:35.865962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b077a8a-59d7-4555-b6f9-9457827ace9d · outbound

This paper cites Are PPO-ed Language Models Hackable?.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Are PPO-ed Language Models Hackable?

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:35.928949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a359a567-a5ea-48b8-bab4-853163c268df · outbound

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

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:35.977601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed84495c-ce25-4a75-8c76-f0d6ba08505b · outbound

This paper cites Jailbreaking leading safety-aligned llms with simple adaptive attacks.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Jailbreaking leading safety-aligned llms with simple adaptive attacks

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:36.047680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fea0ec6-61d4-4d00-aa42-eef9b3cf69bf · outbound

This paper cites Does Refusal Training in LLMs Generalize to the Past Tense?.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Does Refusal Training in LLMs Generalize to the Past Tense?

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:36.084546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec056e70-a0bf-40d1-87a5-ffe022dfc284 · outbound

This paper cites Does refusal training in llms generalize to the past tense? InThe Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Does refusal training in llms generalize to the past tense? InThe Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:36.213690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a7de3c8-ddd0-42b6-9c48-785eba686cbe · outbound

This paper cites Bowman, Ethan Perez, Roger B.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Bowman, Ethan Perez, Roger B

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:36.303948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f92f486-5722-4298-9119-79da1760dfc2 · outbound

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

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Gemini: A Family of Highly Capable Multimodal Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:36.428626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3aba117-b1ff-40dd-921b-6140cac603f1 · outbound

This paper cites Surro- gateprompt: Bypassing the safety filter of text-to-image models via substitution.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Surro- gateprompt: Bypassing the safety filter of text-to-image models via substitution

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:36.525826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7739b3f9-3994-46b0-826b-960823cce346 · outbound

This paper cites Qwen Technical Report.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Qwen Technical Report

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:36.554045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b346aeeb-be63-4fe1-9478-41fe118ee20b · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:36.686698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a633e9ce-f650-46b3-bd21-9df0549dcbef · outbound

This paper cites How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:36.791950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e41f6a8a-e9f9-4042-9641-5bcc6b2df7a1 · outbound

This paper cites Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:36.898264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3018bdf-9640-480a-8863-347328d5ded5 · outbound

This paper cites CLARE: Cognitive Load Assessment in REaltime with Multimodal Data.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses CLARE: Cognitive Load Assessment in REaltime with Multimodal Data

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:36.977659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6386057-4902-4bd3-8347-511b75b75692 · outbound

This paper cites Safety-tuned llamas: Lessons from improving the safety of large language models that follow instructions.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Safety-tuned llamas: Lessons from improving the safety of large language models that follow instructions

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:37.119417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9714b2ec-69f2-40db-9f43-a930fd320da8 · outbound

This paper cites an unresolved cited work.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:37.216242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34530978-c609-4bd9-a876-bac5191efeda · outbound

This paper cites Camelai domain expert datasets (physics, math, chemistry & biology), 2023.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Camelai domain expert datasets (physics, math, chemistry & biology), 2023

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:37.321962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0596d4c6-4e43-4580-9e75-31ef44c45463 · outbound

This paper cites Abu-Ghazaleh, M.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Abu-Ghazaleh, M

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:37.468338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 049cd096-529f-41f3-a266-a0ea331e1ad1 · outbound

This paper cites Synneure: Intelligent human-machine teamwork in virtual space.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Synneure: Intelligent human-machine teamwork in virtual space

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:37.530953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12a379a3-78ae-46e8-95f9-842f97684580 · outbound

This paper cites Pappas, Florian Tram` er, Hamed Hassani, and Eric Wong.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Pappas, Florian Tram` er, Hamed Hassani, and Eric Wong

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:37.594081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77568c13-4dc4-4203-bf10-059230c62010 · outbound

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

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:37.655290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30779e11-7784-4282-91b0-1954946d0ce4 · outbound

This paper cites Pappas, and Eric Wong.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Pappas, and Eric Wong

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:37.745718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32e7f717-16b9-4033-a048-8ed85123dc67 · outbound

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

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses StruQ: Defending Against Prompt Injection with Structured Queries

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:37.843859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 431632c8-01bb-403c-b47c-a9451766b5ef · outbound

This paper cites When LLM meets DRL: advancing jailbreaking efficiency via drl-guided search.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses When LLM meets DRL: advancing jailbreaking efficiency via drl-guided search

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:37.955176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83850c27-a627-4be6-86ff-bd3abf98e28d · outbound

This paper cites RL-JACK: Reinforcement Learning-powered Black-box Jailbreaking Attack against LLMs.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses RL-JACK: Reinforcement Learning-powered Black-box Jailbreaking Attack against LLMs

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:38.012962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50577956-3357-40d7-a052-48ca48250d2a · outbound

This paper cites Leveraging the Context through Multi-Round Interactions for Jailbreaking Attacks.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Leveraging the Context through Multi-Round Interactions for Jailbreaking Attacks

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:38.087372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b6fa656-4f8b-4db8-b93a-60076a35138b · outbound

This paper cites Prompt Injection Attacks on Large Language Models in Oncology.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Prompt Injection Attacks on Large Language Models in Oncology

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:38.152499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bedcacc9-ef63-49fd-9418-127f1168ef4c · outbound

This paper cites Cogstack, 2023.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Cogstack, 2023

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:38.235834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93f9ec51-6210-42a8-a429-997c188f1592 · outbound

This paper cites A Jailbroken GenAI Model Can Cause Substantial Harm: GenAI-powered Applications are Vulnerable to PromptWares.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses A Jailbroken GenAI Model Can Cause Substantial Harm: GenAI-powered Applications are Vulnerable to PromptWares

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:38.278442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1a0e7d8-929c-45da-9d63-741195854150 · outbound

This paper cites MoJE: Mixture of Jailbreak Experts, Naive Tabular Classifiers as Guard for Prompt Attacks.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses MoJE: Mixture of Jailbreak Experts, Naive Tabular Classifiers as Guard for Prompt Attacks

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:38.354404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c45bcb92-58bf-43b9-a57b-83d2ccbcb919 · outbound

This paper cites Moje: Mixture of jailbreak experts, naive tabular classifiers as guard for prompt attacks.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Moje: Mixture of jailbreak experts, naive tabular classifiers as guard for prompt attacks

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:38.438918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab74301b-214b-4d37-b953-ee73a08f750b · outbound

This paper cites alpaca-gpt4-cot, 2024.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses alpaca-gpt4-cot, 2024

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:38.557256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f38120c-10fc-4679-954b-6e5b77f129bb · outbound

This paper cites Dataset and lessons learned from the 2024 satml LLM capture-the-flag competition.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Dataset and lessons learned from the 2024 satml LLM capture-the-flag competition

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:38.623405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a0ab53c-274f-4eea-9840-214d7c8b968b · outbound

This paper cites AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:38.687859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00863392-c6b6-418d-a1df-f21c64a6756a · outbound

This paper cites Attack prompt generation for red teaming and defending large language models.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Attack prompt generation for red teaming and defending large language models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:38.782483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9817fec3-0c68-4669-a3f1-b040e5fcea88 · outbound

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

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:38.849327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c0115b3-6007-4d3b-a37c-5413d25effe7 · outbound

This paper cites Pandora: Jailbreak GPTs by Retrieval Augmented Generation Poisoning.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Pandora: Jailbreak GPTs by Retrieval Augmented Generation Poisoning

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:38.931982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe063ec7-405b-46c2-bccd-e3c714248afd · outbound

This paper cites Multilingual jailbreak challenges in large language models.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Multilingual jailbreak challenges in large language models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:39.106482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e4a384a-071d-4ea2-9755-6c5ee37db158 · outbound

This paper cites A wolf in sheep’s clothing: Generalized nested jailbreak prompts can fool large language models easily.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses A wolf in sheep’s clothing: Generalized nested jailbreak prompts can fool large language models easily

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:39.377432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03e90c74-720b-4f37-b830-b4c646a49900 · outbound

This paper cites Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:39.433419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7191af2-caa0-40af-ba24-745f0d852e4f · outbound

This paper cites Harnessing Task Overload for Scalable Jailbreak Attacks on Large Language Models.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Harnessing Task Overload for Scalable Jailbreak Attacks on Large Language Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:39.483290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7645fa9-ea0d-47a0-a6de-365ab87a2eb1 · outbound

This paper cites BELLS: A Framework Towards Future Proof Benchmarks for the Evaluation of LLM Safeguards.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses BELLS: A Framework Towards Future Proof Benchmarks for the Evaluation of LLM Safeguards

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:39.537797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12484ebc-aed0-47c4-b236-83de6b3fcc95 · outbound

This paper cites h4rm3l: A language for Composable Jailbreak Attack Synthesis.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses h4rm3l: A language for Composable Jailbreak Attack Synthesis

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:39.619070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f7eb929-631e-42f1-a104-96d669327d06 · outbound

This paper cites Multi-turn jailbreaking large language models via attention shifting.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Multi-turn jailbreaking large language models via attention shifting

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:39.672069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9594e70f-3e35-4f86-aa52-c6c430098b00 · outbound

This paper cites VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:39.742694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02103ce5-3b21-4a7d-aa4c-47433d021e50 · outbound

This paper cites Atoxia: Red-teaming Large Language Models with Target Toxic Answers.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Atoxia: Red-teaming Large Language Models with Target Toxic Answers

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:39.796732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e408f8ef-b6a3-48a5-bccf-d2bfce19d96e · outbound

This paper cites Vr-hand-in-hand: Using virtual reality (VR) hand tracking for hand-object data annotation.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Vr-hand-in-hand: Using virtual reality (VR) hand tracking for hand-object data annotation

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:39.931308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddb40eed-ee9a-48ad-af23-4dd5eaa62854 · outbound

This paper cites A comprehensive survey of attack techniques, implementation, and mitigation strategies in large language models.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses A comprehensive survey of attack techniques, implementation, and mitigation strategies in large language models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:40.034725Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 621c4223-71ea-4e8f-8f65-626e4fd54b5f · outbound

This paper cites Unbridled icarus: A survey of the potential perils of image inputs in multimodal large language model security.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Unbridled icarus: A survey of the potential perils of image inputs in multimodal large language model security

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:40.115576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff93b40b-3006-4fca-bfc7-8ceef6c257e9 · outbound

This paper cites JailbreakLens: Visual Analysis of Jailbreak Attacks Against Large Language Models.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses JailbreakLens: Visual Analysis of Jailbreak Attacks Against Large Language Models

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:40.187719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41d41791-47f3-478b-8b93-8b1a43fcb9fe · outbound

This paper cites Safety alignment in NLP tasks: Weakly aligned summarization as an in-context attack.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Safety alignment in NLP tasks: Weakly aligned summarization as an in-context attack

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:40.259864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc437b38-c7f0-44d9-9a3f-f019cf882af7 · outbound

This paper cites Cross-Task Defense: Instruction-Tuning LLMs for Content Safety.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Cross-Task Defense: Instruction-Tuning LLMs for Content Safety

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:40.395617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0104abb8-b93e-4a6d-ba73-08658c0f765b · outbound

This paper cites Merging Improves Self-Critique Against Jailbreak Attacks.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Merging Improves Self-Critique Against Jailbreak Attacks

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:40.483282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db601228-2c5c-4aa0-865b-c89d4baef68e · outbound

This paper cites MART: improving LLM safety with multi-round automatic red-teaming.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses MART: improving LLM safety with multi-round automatic red-teaming

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:40.543033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4c1acff-d1c7-4c9a-8f25-cb5f0c6c7363 · outbound

This paper cites Coercing LLMs to do and reveal (almost) anything.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Coercing LLMs to do and reveal (almost) anything

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:40.590605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbb98816-ca6a-40f5-96a0-89c93ed6d197 · outbound

This paper cites Attacking Large Language Models with Projected Gradient Descent.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Attacking Large Language Models with Projected Gradient Descent

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:40.661962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2d13794-9a2b-4399-9469-ee2f79f5efd0 · outbound

This paper cites AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:40.793268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea59c527-9285-4805-8af7-78b1f2e8efef · outbound

This paper cites Emerging Vulnerabilities in Frontier Models: Multi-Turn Jailbreak Attacks.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Emerging Vulnerabilities in Frontier Models: Multi-Turn Jailbreak Attacks

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:40.938534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcd95c5d-ffb9-484a-b7fc-9d929a2e496a · outbound

This paper cites Breach By A Thousand Leaks: Unsafe Information Leakage in `Safe' AI Responses.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Breach By A Thousand Leaks: Unsafe Information Leakage in `Safe' AI Responses

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:41.056143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f41054c-378c-4f36-a00b-8c506c3c32b4 · outbound

This paper cites Gradient-based adversarial attacks against text transformers.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Gradient-based adversarial attacks against text transformers

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:41.188536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4ad2add-d635-41d4-859f-6f32aa0172ad · outbound

This paper cites Cold-attack: Jailbreaking llms with stealthiness and controllability.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Cold-attack: Jailbreaking llms with stealthiness and controllability

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:41.328475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d461019a-a9cc-49b4-bdad-6cf6e54bf68f · outbound

This paper cites From chatgpt to threatgpt: Impact of generative AI in cybersecurity and privacy.IEEE Access, 11:80218–80245, 2023.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses From chatgpt to threatgpt: Impact of generative AI in cybersecurity and privacy.IEEE Access, 11:80218–80245, 2023

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:41.550062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3301909c-d3bb-4f92-aac1-796af4abbf4f · outbound

This paper cites an unresolved cited work.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Unresolved cited work

Reference 64

Resolution: parse uncertain; no resolver link, observed 2026-08-04T09:25:41.479378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42915daa-e987-4308-a05b-cfa38d400ce0 · outbound

This paper cites Gajera, and Chitta Baral.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Gajera, and Chitta Baral

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:41.823447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6791c844-f679-405d-9538-5d0b15001a93 · outbound

This paper cites Wildguard: Open one-stop moderation tools for safety risks, jailbreaks, and refusals of llms.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Wildguard: Open one-stop moderation tools for safety risks, jailbreaks, and refusals of llms

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:41.701831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d9b2e1d-9a45-4dac-b6bc-f9f8ed73cb27 · outbound

This paper cites Privacy of federated QR decomposition using additive secure multiparty compu- tation.IEEE Trans.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Privacy of federated QR decomposition using additive secure multiparty compu- tation.IEEE Trans

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:42.148660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43b66e3c-e880-4716-a81e-adb2da2b930e · outbound

This paper cites an unresolved cited work.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Unresolved cited work

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:41.985748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fe12d56-4d6b-427d-8c8b-16655549bc71 · outbound

This paper cites Springer Briefs in Computer Science.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Springer Briefs in Computer Science

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:42.429264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cc54660-f3a2-4a99-918c-f20b7b49f2c7 · outbound

This paper cites Query-based adversarial prompt generation.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Query-based adversarial prompt generation

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:42.308793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0735b77b-8282-401f-8bfe-7b518102fb1a · outbound

This paper cites Gradient cuff: Detecting jailbreak attacks on large language models by exploring refusal loss landscapes.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Gradient cuff: Detecting jailbreak attacks on large language models by exploring refusal loss landscapes

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:42.631277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 455d9866-9f50-4a02-8f64-8bf5c5e63266 · outbound

This paper cites Defending against indirect prompt injection attacks with spotlighting.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Defending against indirect prompt injection attacks with spotlighting

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:42.520819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c51da07-703f-4b26-94b6-c2c89dfdf775 · outbound

This paper cites an unresolved cited work.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Unresolved cited work

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:42.795114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16c3402c-6f54-42f2-840b-f2182031128a · outbound

This paper cites SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidance.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidance

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:42.743728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96ae2779-3cc2-4ded-9764-a56c00db3b65 · outbound

This paper cites Summon a Demon and Bind it: A Grounded Theory of LLM Red Teaming.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Summon a Demon and Bind it: A Grounded Theory of LLM Red Teaming

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:42.921586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 592b08cf-b8fc-47db-84f2-61193b21fecc · outbound

This paper cites Catastrophic jailbreak of open-source llms via exploiting generation.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Catastrophic jailbreak of open-source llms via exploiting generation

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:42.848076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4caaa46-b992-4e71-9ba7-e9340233975d · outbound

This paper cites Beavertails: Towards improved safety alignment of LLM via a human-preference dataset.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Beavertails: Towards improved safety alignment of LLM via a human-preference dataset

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:43.019507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd32e0e4-2fb8-4cb4-882b-c3330f9b24c6 · outbound

This paper cites Baseline Defenses for Adversarial Attacks Against Aligned Language Models.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:42.972944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a4f3330-ff82-440f-b9a5-8e93d4572fc1 · outbound

This paper cites Automated progressive red teaming.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Automated progressive red teaming

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:43.222934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a66055a-f2f6-4ede-9f09-0dac4dcfb177 · outbound

This paper cites Improved techniques for optimization-based jailbreaking on large language models.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Improved techniques for optimization-based jailbreaking on large language models

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:43.117969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b67286f1-d679-48a7-8b1a-f8d062120594 · outbound

This paper cites How Well Do LLMs Handle Cantonese? Benchmarking Cantonese Capabilities of Large Language Models.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses How Well Do LLMs Handle Cantonese? Benchmarking Cantonese Capabilities of Large Language Models

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:43.462117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 993f03bd-2797-4073-b236-6c4772f2f376 · outbound

This paper cites Artprompt: ASCII art-based jailbreak attacks against aligned llms.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Artprompt: ASCII art-based jailbreak attacks against aligned llms

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:43.358431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc745b0d-06b8-4b6d-aa5d-f51d89c7c6e0 · outbound

This paper cites An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:43.691276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b48ce965-8368-4aac-839f-57502c835e31 · outbound

This paper cites Wildteaming at scale: From in-the-wild jailbreaks to (adversarially) safer language models.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Wildteaming at scale: From in-the-wild jailbreaks to (adversarially) safer language models

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:43.586510Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58b33b15-decc-4f83-94c5-397ff037b586 · outbound

This paper cites GUARD: role-playing to generate natural-language jailbreakings to test guideline adherence of large language models.CoRR, abs/2402.03299, 2024.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses GUARD: role-playing to generate natural-language jailbreakings to test guideline adherence of large language models.CoRR, abs/2402.03299, 2024

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:43.924124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72cb0e55-3ef8-44af-b1be-3c2f0f1f0849 · outbound

This paper cites RED QUEEN: Safeguarding Large Language Models against Concealed Multi-Turn Jailbreaking.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses RED QUEEN: Safeguarding Large Language Models against Concealed Multi-Turn Jailbreaking

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:43.834739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ac69714-b70b-42f7-9c0a-9d2a565ae173 · outbound

This paper cites airoboros-2.2, 2023.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses airoboros-2.2, 2023

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:44.167467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41e4b29d-9027-4200-8c48-8ec8fb5729b6 · outbound

This paper cites Jailbreakzoo: Survey, landscapes, and horizons in jailbreaking large language and vision-language models.CoRR, abs/2407.01599, 2024.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Jailbreakzoo: Survey, landscapes, and horizons in jailbreaking large language and vision-language models.CoRR, abs/2407.01599, 2024

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:44.048608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61c77a38-f94c-43af-8797-e095fed36918 · outbound

This paper cites Adversaries Can Misuse Combinations of Safe Models.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Adversaries Can Misuse Combinations of Safe Models

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:44.450683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4b97758-ce27-4c7d-9aab-6405ad414d27 · outbound

This paper cites Dragan, Aditi Raghunathan, and Jacob Steinhardt.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Dragan, Aditi Raghunathan, and Jacob Steinhardt

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:44.303783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 335c8800-3be9-4431-add4-ab1500a44bb0 · outbound

This paper cites Prompt Injection Attacks in Defended Systems.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Prompt Injection Attacks in Defended Systems

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:44.752795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c932a8fe-9906-402a-b4f3-6e6a69f40eab · outbound

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

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Exploiting programmatic behavior of llms: Dual-use through standard security attacks

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:44.645801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d03ab2ff-9879-4317-98e8-9dd6494ca598 · outbound

This paper cites Testing the Limits of Jailbreaking Defenses with the Purple Problem.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Testing the Limits of Jailbreaking Defenses with the Purple Problem

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:45.047622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59b80ef8-a9d3-4ade-9607-bfd534c63dad · outbound

This paper cites Break the Breakout: Reinventing LM Defense Against Jailbreak Attacks with Self-Refinement.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Break the Breakout: Reinventing LM Defense Against Jailbreak Attacks with Self-Refinement

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:44.871354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 510fa07b-1d80-43a3-9c68-e3914854dc9c · outbound

This paper cites Certifying LLM Safety against Adversarial Prompting.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Certifying LLM Safety against Adversarial Prompting

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:45.397309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9abbf7f-1f7f-47bf-9ac7-84ff298caac9 · outbound

This paper cites Empirical Analysis of Large Vision-Language Models against Goal Hijacking via Visual Prompt Injection.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Empirical Analysis of Large Vision-Language Models against Goal Hijacking via Visual Prompt Injection

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:45.204025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91d877c2-d706-4788-9dcf-4d42d5b19472 · outbound

This paper cites Platypus: Quick, Cheap, and Powerful Refinement of LLMs.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Platypus: Quick, Cheap, and Powerful Refinement of LLMs

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:45.762344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ab876c1-6575-4d55-b711-3fb3217f109b · outbound

This paper cites Open Sesame! Universal Black Box Jailbreaking of Large Language Models.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Open Sesame! Universal Black Box Jailbreaking of Large Language Models

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:45.557792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16f4b4f1-0897-4ce5-b30d-3bc42dd98d7d · outbound

This paper cites A Cross-Language Investigation into Jailbreak Attacks in Large Language Models.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses A Cross-Language Investigation into Jailbreak Attacks in Large Language Models

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:45.961893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c28a4b1-0b8e-4d39-9786-d5530b3e1275 · outbound

This paper cites Multi-step jailbreaking privacy attacks on chatgpt.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Multi-step jailbreaking privacy attacks on chatgpt

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:45.887588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation c6354cbb-4b4a-47b8-b2c4-482deab1990e · inbound

One Goal, Many Commands: Characterizing Denylist Fragility in AI Agents cites this paper.

One Goal, Many Commands: Characterizing Denylist Fragility in AI Agents SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-07-07T03:17:13.442555Z

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 dcc69231-6c3f-4338-9e8e-94f2e02cdc18 · inbound

Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systems cites this paper.

Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systems SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-07-07T03:17:13.442555Z

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 f9cbcb8c-5570-4e46-a76b-b0d6fa736dd8 · inbound

SoK: Intent-Oriented Systematization of Multi-Turn LLM Jailbreaks cites this paper.

SoK: Intent-Oriented Systematization of Multi-Turn LLM Jailbreaks SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-06T00:32:02.668360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.