Paper Citation Record · LEDGER

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models

As of 10 August 2026, this Paper Citation Record lists 67 of 67 outbound references and 2 inbound Pith citation observations for arXiv:2501.18280.

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

pith.paper-citation-record.v1
2501.18280 v3

Coverage vector

measured 67 of 67 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T00:12:05.079388Z

measured 69 of 69 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T19:26:13.670577Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-11T22:06:14.567526Z

Reference resolution

67 of 67 outbound references displayed

verified exact0
verified fuzzy25
unresolved42
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 16fccada-03e5-4f21-87c2-41d57c520cb2 · outbound

This paper cites Language models are few-shot learners.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Language models are few-shot learners

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.755726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e07a32db-a7b3-481e-8aaa-86e627faf073 · outbound

This paper cites Understanding searches better than ever before.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Understanding searches better than ever before

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:12:06.179282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fa899b7f-a911-4fd9-a352-be61baa99090 · outbound

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

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.765931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90aab91d-344c-4367-a19e-234c10dee887 · outbound

This paper cites Openai platform: Moderation, 2025.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Openai platform: Moderation, 2025

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:12:06.164078Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 90314a44-dcf2-4def-bdda-15af265335fa · outbound

This paper cites Robust Safety Classifier for Large Language Models: Adversarial Prompt Shield.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Robust Safety Classifier for Large Language Models: Adversarial Prompt Shield

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.776479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5eda0616-121b-4283-b602-64df299dcbb0 · outbound

This paper cites A General Language Assistant as a Laboratory for Alignment.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models A General Language Assistant as a Laboratory for Alignment

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.781717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7118279-5a98-4f15-8594-e62a0fb87705 · outbound

This paper cites Aligning generative language models with human values.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Aligning generative language models with human values

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:12:06.147932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation de5bf61b-29c2-48ce-9356-486ea089182c · outbound

This paper cites Jailbroken: How does llm safety training fail? Advances in Neural Information Processing Systems, 36, 2024.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Jailbroken: How does llm safety training fail? Advances in Neural Information Processing Systems, 36, 2024

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.791906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09198dd9-bab1-432a-909d-0df764533684 · outbound

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

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.796557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1735f1c-1465-4148-906e-e26159bcfda6 · outbound

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

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.801686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a875ab67-6a8f-441f-a8ef-90f07838ef9f · outbound

This paper cites Detecting Language Model Attacks with Perplexity.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Detecting Language Model Attacks with Perplexity

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.806790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 204a5916-d829-40c7-b354-df86aca3b8e1 · outbound

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

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.812015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f26dd78-4c35-4556-8f79-98f7892de47d · outbound

This paper cites Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.817181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e2dbc9f-5f48-4857-bb17-fa94c89b086e · outbound

This paper cites Defending chatgpt against jailbreak attack via self-reminders.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Defending chatgpt against jailbreak attack via self-reminders

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:12:06.121849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 67b2e727-6d7f-4a5d-aad4-97c6220adad5 · outbound

This paper cites Intention Analysis Makes LLMs A Good Jailbreak Defender.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Intention Analysis Makes LLMs A Good Jailbreak Defender

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.826574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a471ada-5486-406e-adee-1645b2067f19 · outbound

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

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Ignore Previous Prompt: Attack Techniques For Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.831463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da3d688a-2342-46c6-ab35-c42f30f790ec · outbound

This paper cites Certifying LLM Safety against Adversarial Prompting.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Certifying LLM Safety against Adversarial Prompting

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.836347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 317c321b-8c17-41c0-a4c4-2ee3557d9ecd · outbound

This paper cites SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.841127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f0ed471-d43b-4a9f-8b68-a3b361c4bcd4 · outbound

This paper cites LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.846129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e107d9a-5896-4eee-ace5-17ba50ef1103 · outbound

This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.851548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11f6dce0-390e-43bc-a2c1-dccbb59c92c4 · outbound

This paper cites Self-Guard: Empower the LLM to Safeguard Itself.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Self-Guard: Empower the LLM to Safeguard Itself

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.857095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc43374e-4398-43a9-9ba4-16363a3ff60a · outbound

This paper cites DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.862010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5bea726-bd84-4d26-9af3-32ed8357fb90 · outbound

This paper cites A holistic approach to undesired content detection in the real world.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models A holistic approach to undesired content detection in the real world

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:12:06.106824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ec2c5be0-a579-4252-b93b-289b9ae89f95 · outbound

This paper cites Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.871771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1eb5fc1-b022-49fb-966a-6abd486771c7 · outbound

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

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.876803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 941745b9-75cd-4f8c-9a7d-aa987e2725d1 · outbound

This paper cites Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.882237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddb4683d-f023-4ce5-a72e-a8bbd28ed04d · outbound

This paper cites DeepInception: Hypnotize Large Language Model to Be Jailbreaker.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models DeepInception: Hypnotize Large Language Model to Be Jailbreaker

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.887440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94499c3c-ab81-4945-b5b5-750891f5101e · outbound

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

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Multi-step Jailbreaking Privacy Attacks on ChatGPT

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.892253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fc10c1d-b014-4764-b825-5addbe44bffb · outbound

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

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Exploiting programmatic behavior of llms: Dual-use through standard security attacks

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:12:06.091140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c3a15c98-eaee-4829-805f-c0d4c988d025 · outbound

This paper cites Exploiting large language models (llms) through deception techniques and persuasion principles.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Exploiting large language models (llms) through deception techniques and persuasion principles

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:12:06.075048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e11f8152-d47f-4d6c-b415-1b67239037d0 · outbound

This paper cites Analyzing the Inherent Response Tendency of LLMs: Real-World Instructions-Driven Jailbreak.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Analyzing the Inherent Response Tendency of LLMs: Real-World Instructions-Driven Jailbreak

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.906792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39f118d1-42d6-48da-bb63-087217f02fd5 · outbound

This paper cites Universal adversarial triggers for attacking and analyzing nlp.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Universal adversarial triggers for attacking and analyzing nlp

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:12:06.059773Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0a469e69-e728-4318-b7bc-9eea77e47255 · outbound

This paper cites Autodan: interpretable gradient-based adversarial attacks on large language models.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Autodan: interpretable gradient-based adversarial attacks on large language models

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:12:06.044739Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5b02c2f7-5736-4687-9504-62f53e08cf5f · outbound

This paper cites Open sesame! universal black-box jailbreaking of large language models.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Open sesame! universal black-box jailbreaking of large language models

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:12:06.028402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a2f9dd0c-457b-46bb-8c32-ecc869ba4e2c · outbound

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

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.925506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a135ce9b-0a0d-47ba-8a25-33d823308d77 · outbound

This paper cites AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.930255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16317c45-5fac-4eb3-9660-099cac7937b2 · outbound

This paper cites Textbugger: Generating adversarial text against real-world applications.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Textbugger: Generating adversarial text against real-world applications

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:12:06.011175Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 663127c6-1629-4d1d-aaef-f5abbc8d91aa · outbound

This paper cites Is bert really robust? a strong baseline for natural language attack on text classification and entailment.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Is bert really robust? a strong baseline for natural language attack on text classification and entailment

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:12:05.995367Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation df57ed7e-81d5-4336-a629-bf6bd43bfcee · outbound

This paper cites A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.944877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 819452cf-c266-4673-a395-025817bf5412 · outbound

This paper cites Tree of Attacks: Jailbreaking Black-Box LLMs Automatically.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Tree of Attacks: Jailbreaking Black-Box LLMs Automatically

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.949794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46956122-903b-4e71-bf10-2f4c100565e5 · outbound

This paper cites Evil Geniuses: Delving into the Safety of LLM-based Agents.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Evil Geniuses: Delving into the Safety of LLM-based Agents

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.954575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95e56b94-677f-47e0-ab62-47944cab4eac · outbound

This paper cites MART: Improving LLM Safety with Multi-round Automatic Red-Teaming.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models MART: Improving LLM Safety with Multi-round Automatic Red-Teaming

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.959460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4b5b320-094e-44a5-bbde-cada50d59d0d · outbound

This paper cites Latent Jailbreak: A Benchmark for Evaluating Text Safety and Output Robustness of Large Language Models.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Latent Jailbreak: A Benchmark for Evaluating Text Safety and Output Robustness of Large Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.964160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c561d7ab-4da3-4796-bef4-5b3ed7ffc3bd · outbound

This paper cites GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.968909Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fef7ec5f-d161-4e49-8561-3ea633c9e6f7 · outbound

This paper cites Text-based prompt injection attack using mathematical functions in modern large language models.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Text-based prompt injection attack using mathematical functions in modern large language models

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:12:05.979906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b2b18247-57fd-4afd-bf77-032169c7324d · outbound

This paper cites Llm prompt recovery.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Llm prompt recovery

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:12:05.963402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 17ff1f8b-e15b-43da-9b80-9da31bfc2cb6 · outbound

This paper cites PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.983389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5059ffa8-97a8-4729-b0ee-15b479520a17 · outbound

This paper cites Mteb: Massive text embedding benchmark.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Mteb: Massive text embedding benchmark

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:12:05.946997Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0ea71be0-db2b-4c96-8b65-d29e69b4a8ca · outbound

This paper cites Sentence-t5: Scalable sentence encoders from pre-trained text-to-text models.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Sentence-t5: Scalable sentence encoders from pre-trained text-to-text models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.992595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7917cc13-f42e-4a6e-8dbc-96b287e21b68 · outbound

This paper cites Nomic Embed: Training a Reproducible Long Context Text Embedder.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Nomic Embed: Training a Reproducible Long Context Text Embedder

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.997118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8813c6c7-fcbc-4afd-b508-477ec795998f · outbound

This paper cites Text Embeddings by Weakly-Supervised Contrastive Pre-training.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Text Embeddings by Weakly-Supervised Contrastive Pre-training

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:05.001580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21da30ca-3956-4733-8728-9b5b8bb1cd46 · outbound

This paper cites Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:05.006210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6212a5f-5ffa-486b-9024-faa39456abc1 · outbound

This paper cites Towards General Text Embeddings with Multi-stage Contrastive Learning.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Towards General Text Embeddings with Multi-stage Contrastive Learning

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:05.012080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d22c5cc3-6eb6-4a84-8a7b-b959ba280e03 · outbound

This paper cites SFR-embedding-mistral:enhance text retrieval with transfer learning.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models SFR-embedding-mistral:enhance text retrieval with transfer learning

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:12:05.920705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a89a2948-4b56-4817-838a-8bfecdfcdbee · outbound

This paper cites Improving text embeddings with large language models.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Improving text embeddings with large language models

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:12:05.884761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation cbd24533-a40b-4d2e-8196-6a77ddcf50c3 · outbound

This paper cites Qwen2.5: A party of foundation models.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Qwen2.5: A party of foundation models

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:12:05.867570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 79734ce8-8070-403a-9c7f-45b21839aa71 · outbound

This paper cites Dataset: sentence-transformers/simple-wiki.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Dataset: sentence-transformers/simple-wiki

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:12:05.852571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fc3a316f-da9f-4e63-9154-9c4e988ba6b6 · outbound

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

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:05.034990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bd284b2-f131-437b-9bff-d3a5fca073f6 · outbound

This paper cites Sparkdesk, 2025.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Sparkdesk, 2025

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:12:05.837170Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 21a2048d-6490-4080-9bed-0c1fa95cdc2a · outbound

This paper cites Intrinsic dimension estimation for robust detection of ai-generated texts.Advances in Neural Information Processing Systems, 36, 2024.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Intrinsic dimension estimation for robust detection of ai-generated texts.Advances in Neural Information Processing Systems, 36, 2024

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:12:05.821466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 12cdb924-9fe1-4b50-be35-8012b350bd7c · outbound

This paper cites Phase Transitions in Large Language Models and the $O(N)$ Model.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Phase Transitions in Large Language Models and the $O(N)$ Model

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:05.049287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 435d67d1-54ac-43ae-9138-9feb4b0b07fb · outbound

This paper cites an unresolved cited work.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Unresolved cited work

Reference 62

Resolution: unresolved; raw_fallback, observed 2026-08-10T00:12:05.803699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 21aaa3b3-8bcf-425a-8233-28c87b58dc77 · outbound

This paper cites an unresolved cited work.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Unresolved cited work

Reference 63

Resolution: unresolved; raw_fallback, observed 2026-08-10T00:12:05.784694Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a2d8671c-890b-444a-a582-8afc9fb11569 · outbound

This paper cites (8) 15 Matrix B is obtained from A by normalizing each row of A.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models (8) 15 Matrix B is obtained from A by normalizing each row of A

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:12:05.767968Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b7e383fd-82c1-4c2f-bbe1-616058c5b8f6 · outbound

This paper cites Gaussian vector in Rm, normalizing it means bi is uniformly distributed on the unit sphere Sm−1.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Gaussian vector in Rm, normalizing it means bi is uniformly distributed on the unit sphere Sm−1

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:12:05.750036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 98134cc6-5157-4a25-876f-1e4c14883352 · outbound

This paper cites (10) When m ≫ 1, b⊤ i bj ∼ N 0, 1 m.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models (10) When m ≫ 1, b⊤ i bj ∼ N 0, 1 m

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:12:05.732676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0ffed183-0be2-4876-b6ad-6f269163d7a8 · outbound

This paper cites # Figure 9: Renormalization uniformly amplifies axial noise and radial signal and therefore pre- serves the SNR. 𝑒̅ 𝑒∗ 𝜃 𝑆!.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models # Figure 9: Renormalization uniformly amplifies axial noise and radial signal and therefore pre- serves the SNR. 𝑒̅ 𝑒∗ 𝜃 𝑆!

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T00:12:05.715799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Pith citing papers

Observation 42b7747e-964d-4fe7-b669-fb29a6f538a6 · inbound

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation cites this paper.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.670577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13287844-7ef9-4188-b156-bc815b70a107 · inbound

Adaptive Prompt Embedding Optimization for LLM Jailbreaking cites this paper.

Adaptive Prompt Embedding Optimization for LLM Jailbreaking Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-11T22:06:14.575357Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.