Paper Citation Record · LEDGER

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation

As of 9 August 2026, this Paper Citation Record lists 57 of 57 outbound references and 0 inbound Pith citation observations for arXiv:2510.10271.

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

pith.paper-citation-record.v1
2510.10271 v2

Coverage vector

measured 57 of 57 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T10:22:09.891717Z

measured 57 of 57 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

57 of 57 outbound references displayed

verified exact0
verified fuzzy0
unresolved56
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 728944a9-36b5-42bf-8dcf-6d9781201f0d · outbound

This paper cites an unresolved cited work.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:03.574802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9afef46-94c6-439b-a238-efa59ab9e450 · outbound

This paper cites Claude language model.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Claude language model

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:03.743142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6e35ae6-f758-4df9-9232-1737f71fd795 · outbound

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

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:03.851082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 157e5ea5-58f2-4249-9d86-3801510b2d1c · outbound

This paper cites Brown, B.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Brown, B

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:03.951929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6bd7700-fd23-4a3b-90b9-e5313f27d944 · outbound

This paper cites Sparks of Artificial General Intelligence: Early experiments with GPT-4.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Sparks of Artificial General Intelligence: Early experiments with GPT-4

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:04.039919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5a51e44-660e-4dca-8c73-cc93bccc1bb9 · outbound

This paper cites an unresolved cited work.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:04.186542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a441a9e7-6922-4492-8447-1f81cf1845f1 · outbound

This paper cites Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:04.265393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71b6b507-8827-4a4b-89e5-17446252900a · outbound

This paper cites an unresolved cited work.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:04.400005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4d3a143-1659-417a-8ea1-5d431b77529c · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:04.530244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a1409cd-e4e7-4cf8-b9a7-1e46bbcb643f · outbound

This paper cites Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:04.668209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2515446-b1cf-410e-89d9-8fd85e5b33ef · outbound

This paper cites Greshake, S.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Greshake, S

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:04.805345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46fb75b0-dfa3-4aea-bacd-daacb0f7926c · outbound

This paper cites Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:04.978108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 348ba7af-6484-45eb-9468-ea3bc8554beb · outbound

This paper cites Chat templates.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Chat templates

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:05.110225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4fe4e10-2fd5-4049-ac51-974d7ac8adc6 · outbound

This paper cites Introducing transformers.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Introducing transformers

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:05.201710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ea74fc1-7106-433e-849b-7252cbd7db0e · outbound

This paper cites Huggingchat.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Huggingchat

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:05.287506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4b9f4cb-8330-4ac1-99e6-8dd5e00d27b8 · outbound

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

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:05.360275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e082453-b2f1-4756-8b56-0ce023bac7d6 · outbound

This paper cites Jiang, Z.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Jiang, Z

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:05.453896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfecbc81-ccc4-4dec-8d15-d5ce61015361 · outbound

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

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:05.603724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61f754cf-153a-424c-ade3-a88610db584b · outbound

This paper cites an unresolved cited work.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:05.684647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1524ba1-1d12-4b1c-908e-477526af40ea · outbound

This paper cites an unresolved cited work.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:05.789203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d006d8b-99f8-4df9-b8d8-2013a75c1818 · outbound

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

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:05.891059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35f62a36-f6d6-4b33-99c6-d55049917d54 · outbound

This paper cites Automatic and Universal Prompt Injection Attacks against Large Language Models.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Automatic and Universal Prompt Injection Attacks against Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:06.011277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e2f4869-4c54-4cdb-94cd-19e859b3735e · outbound

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

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Prompt Injection attack against LLM-integrated Applications

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:06.138849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19b534a4-6e5a-464e-a412-efbfac4a5edf · outbound

This paper cites an unresolved cited work.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:06.213915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4472f6e-e681-4e12-b2cb-0b71e3568005 · outbound

This paper cites Introducing llama guard 3.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Introducing llama guard 3

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:06.308868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3c4c724-acda-410e-bc94-752afa465cd1 · outbound

This paper cites Introducing prompt guard.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Introducing prompt guard

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:06.432278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77c11ab9-d157-41b4-826b-b86b277221f5 · outbound

This paper cites Chat markup language chatml.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Chat markup language chatml

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:06.556109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb2dbc81-a199-41f3-8738-a90e501bfeba · outbound

This paper cites About ollama.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation About ollama

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:06.630050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7831d7a6-2ff1-497d-85c3-21cb5b7100d0 · outbound

This paper cites Create chat completion.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Create chat completion

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:06.732089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f29fc3a7-a5f8-4b2f-987c-f87ea6264736 · outbound

This paper cites Introducing chatgpt.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Introducing chatgpt

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:06.900198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec899d2c-5b3f-46a5-8ce6-90a60ab65db3 · outbound

This paper cites OpenAI Completion API.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation OpenAI Completion API

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:07.032122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4104159c-59e3-4346-a2db-d1a66c7ac68e · outbound

This paper cites GPT-4 Technical Report.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation GPT-4 Technical Report

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:07.198025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33d5d6ac-45d1-4114-b1e6-cc9ab44fa55f · outbound

This paper cites Introducing chatml format.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Introducing chatml format

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:07.338362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1b23f83-349b-4a6f-a17a-29970c58fde1 · outbound

This paper cites Ouyang, J.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Ouyang, J

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:07.511872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a54cfb71-6784-4158-b501-c151656a00ed · outbound

This paper cites Instruction Tuning with GPT-4.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Instruction Tuning with GPT-4

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:07.661544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 375a933e-c847-4516-b0d9-e9a1dfb28f56 · outbound

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

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Ignore Previous Prompt: Attack Techniques For Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:07.828867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7411ff87-2dfe-4889-b9ac-1bc99832d9ba · outbound

This paper cites About poe.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation About poe

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:07.897318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7c54e29-1fe3-41a6-b55e-63eeb0b820a7 · outbound

This paper cites Introducing pytorch.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Introducing pytorch

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:07.976952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 642bc178-87cc-4a5e-a3b9-3c081a68670d · outbound

This paper cites an unresolved cited work.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Unresolved cited work

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:08.121307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76317485-b3cf-4915-baf9-b699272536e3 · outbound

This paper cites an unresolved cited work.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Unresolved cited work

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:08.239250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85d1fb85-fe48-4d98-8455-c4839a531f2e · outbound

This paper cites an unresolved cited work.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Unresolved cited work

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:08.327732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63cb829f-3c6f-4408-af7f-e579dd4ee02a · outbound

This paper cites Taori, I.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Taori, I

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:08.395182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b02a5e29-0ffb-44a5-bff0-e3c8e8b5626f · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:08.461117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78279eed-d985-4b15-8846-15b52593e725 · outbound

This paper cites Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:08.545695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c13538bb-38e7-4803-888f-7ed55f07d2a7 · outbound

This paper cites an unresolved cited work.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Unresolved cited work

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:08.612733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d4b181d-9f7d-423a-bdce-6fc637912ce1 · outbound

This paper cites Self-Instruct: Aligning Language Models with Self-Generated Instructions.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Self-Instruct: Aligning Language Models with Self-Generated Instructions

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:08.696120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 158347e9-6d12-4fe2-bbca-df8c4297d188 · outbound

This paper cites SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:08.785775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdd2357e-03ef-4e8f-b96c-871eaca5bcf3 · outbound

This paper cites an unresolved cited work.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Unresolved cited work

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:08.875820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7365ede4-3072-49fb-a459-9afcc30186b9 · outbound

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

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:08.950776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48bf1763-1905-46a0-a554-9494f7b94777 · outbound

This paper cites ShieldGemma: Generative AI Content Moderation Based on Gemma.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation ShieldGemma: Generative AI Content Moderation Based on Gemma

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:09.048406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bee77cb5-d75b-416c-a846-777e694ab016 · outbound

This paper cites How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:09.180107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91047aa9-7dc6-4014-a46f-73eaca58a3e4 · outbound

This paper cites Zhang, Z.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Zhang, Z

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:09.354859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e61ca328-ed06-4a87-b3cb-ca98474b82bc · outbound

This paper cites an unresolved cited work.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Unresolved cited work

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:09.483407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90b2b8a4-c288-429f-8acd-8829c9ae3135 · outbound

This paper cites Fine-Tuning Language Models from Human Preferences.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Fine-Tuning Language Models from Human Preferences

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:09.583758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4351cbb8-6275-45a7-b9d7-4cf44c7c4e11 · outbound

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

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 55

Resolution: malformed identifier; no resolver link, observed 2026-08-04T10:22:09.703745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbc348ba-5912-4b86-9a35-4b0be017d8df · outbound

This paper cites an unresolved cited work.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Unresolved cited work

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:09.797025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82297acc-b6da-4e70-9fa9-1cf719b5dd32 · outbound

This paper cites A:(Sure, here is an example of) websites: * The Red Room: A dark Web forum known for its illicit activities, including organ trafficking.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation A:(Sure, here is an example of) websites: * **The Red Room**: A dark Web forum known for its illicit activities, including organ trafficking

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:09.891717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.